arXivSub Start free trial

ICCV 2023 Papers with Code

IEEE/CVF International Conference on Computer Vision Β· 743 papers with a public code repository

3D Human Mesh Recovery with Sequentially Global Rotation Estimation

Dongkai Wang (Peking University), Shiliang Zhang (Peking University)

CodePose EstimationConvolutional Neural NetworkSupervised Fine-TuningImageMesh

🎯 What it does: A Sequentially Global Rotation Estimation (SGRE) method is proposed for 3D human mesh recovery from monocular RGB images, directly predicting the global rotation matrices of each joint.

3D Implicit Transporter for Temporally Consistent Keypoint Discovery

Chengliang Zhong (Tsinghua University), Jian Zhao (Tsinghua University)

CodeObject DetectionRobotic IntelligencePoint Cloud

🎯 What it does: A self-supervised 3D Implicit Transporter is proposed, capable of discovering spatiotemporally consistent key points from continuous point cloud sequences, and utilizing these key points for goal-driven 3D object manipulation.

3D Neural Embedding Likelihood: Probabilistic Inverse Graphics for Robust 6D Pose Estimation

Guangyao Zhou (Google DeepMind), Vikash K. Mansinghka (Massachusetts Institute of Technology)

CodePose EstimationImage

🎯 What it does: Proposes 3D Neural Embedding Likelihood (3DNEL), a 6D object pose estimation framework based on probabilistic inverse graphics.

3D Semantic Subspace Traverser: Empowering 3D Generative Model with Shape Editing Capability

Ruowei Wang (Sichuan University), Qijun Zhao (Sichuan University)

CodeGenerationData SynthesisGenerative Adversarial NetworkPoint CloudMesh

🎯 What it does: A 3D Semantic Subspace Traverser is proposed, which can achieve 3D shape generation and semantic editing under implicit function representation.

3DMiner: Discovering Shapes from Large-Scale Unannotated Image Datasets

Ta-Ying Cheng (University of Oxford), Niki Trigoni (University of Oxford)

CodeObject DetectionSegmentationRepresentation LearningTransformerContrastive LearningSimultaneous Localization and MappingImage

🎯 What it does: On a large-scale unlabeled image dataset, without the need for 3D annotations, camera information, or key points, the 3DMiner pipeline automatically mines and reconstructs 3D shapes;

3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object Detection

Changyong Shu (Houmo AI), Yifan Liu (University of Adelaide)

CodeObject DetectionDepth EstimationAutonomous DrivingKnowledge DistillationTransformerPoint Cloud

🎯 What it does: A 3D Point Pose Encoding (3DPPE) is proposed for Transformer-based multi-camera 3D object detection, utilizing depth estimation to project pixels into 3D space to obtain accurate point position information and embed features.

4D Myocardium Reconstruction with Decoupled Motion and Shape Model

Xiaohan Yuan (Southeast University), Yangang Wang (Southeast University)

CodeSegmentationGenerationAuto EncoderImagePoint CloudMagnetic Resonance Imaging

🎯 What it does: A 4D myocardial reconstruction method based on implicit functions is proposed, which can predict the complete myocardial shape and its temporal evolution from sparse CMR slice point clouds.

A Benchmark for Chinese-English Scene Text Image Super-Resolution

Jianqi Ma (Hong Kong Polytechnic University), Lei Zhang (Hong Kong Polytechnic University)

CodeRestorationSuper ResolutionConvolutional Neural NetworkImageBenchmark

🎯 What it does: This paper constructs a realistic Chinese-English text image super-resolution benchmark dataset, Real-CE, and proposes a dual supervision learning method based on text edges to enhance the reconstruction quality of Chinese characters.

A Complete Recipe for Diffusion Generative Models

Kushagra Pandey (University of California), Stephan Mandt (University of California)

CodeGenerationData SynthesisDiffusion modelScore-based ModelImageStochastic Differential EquationOrdinary Differential Equation

🎯 What it does: This paper proposes a complete design framework for constructing forward diffusion processes that satisfy a given target distribution, and introduces a new diffusion model called Phase Space Langevin Diffusion (PSLD) within this framework.

A Fast Unified System for 3D Object Detection and Tracking

Thomas Heitzinger (Vienna University of Technology), Martin Kampel (Vienna University of Technology)

CodeObject DetectionObject TrackingPose EstimationConvolutional Neural NetworkTransformerPoint Cloud

🎯 What it does: An end-to-end unified system named FUS3D has been designed and implemented, capable of achieving real-time 3D object detection and multi-object tracking on edge devices using only depth maps.

A Generalist Framework for Panoptic Segmentation of Images and Videos

Ting Chen (Google Deepmind), David J. Fleet (Google Deepmind)

CodeObject TrackingSegmentationTransformerDiffusion modelImageVideo

🎯 What it does: A conditional discrete diffusion model Pix2SeqD is proposed for unified processing of panoramic segmentation tasks for images and videos.

A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition

Andong Deng (University of Central Florida), Chen Chen (University of Central Florida)

CodeDomain AdaptationAnomaly DetectionRepresentation LearningConvolutional Neural NetworkTransformerSupervised Fine-TuningContrastive LearningVideoBenchmark

🎯 What it does: A new video action recognition benchmark BEAR is proposed, collecting action datasets from 18 sources across 5 domains (anomaly, gesture, daily, sports, teaching), and systematically evaluating 6 mainstream video models under various settings such as standard fine-tuning, few-shot fine-tuning, unsupervised domain adaptation, and zero-shot learning.

A Soft Nearest-Neighbor Framework for Continual Semi-Supervised Learning

Zhiqi Kang (Universite Grenoble Alpes), Karteek Alahari

CodeClassificationKnowledge DistillationContrastive LearningImage

🎯 What it does: A soft nearest neighbor framework for continuous semi-supervised learning, NNCSL, is proposed.

A step towards understanding why classification helps regression

Silvia L. Pintea (Delft University of Technology), Jan C. van Gemert (Delft University of Technology)

CodeDepth EstimationConvolutional Neural NetworkImageVideo

🎯 What it does: This paper explores why adding classification loss can improve performance in deep regression tasks, and clarifies that its main role is to compensate for the impact of uneven sample distribution.

A Unified Continual Learning Framework with General Parameter-Efficient Tuning

Qiankun Gao (Peking University), Jian Zhang (Peking University)

CodeClassificationOptimizationTransformerPrompt EngineeringImage

🎯 What it does: A general Learning-Accumulation-Integration (LAE) framework is proposed, which utilizes any parameter-efficient tuning (PET) modules (such as Adapter, LoRA, Prefix) for continual learning on pre-trained models, and achieves memoryless continual learning through the integration of online and offline PET modules.

A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidance

Ian Colbert (Advanced Micro Devices), Jakoba Petri-Koenig (Advanced Micro Devices)

CodeClassificationSuper ResolutionConvolutional Neural NetworkImage

🎯 What it does: The A2Q method is proposed, which trains quantized neural networks to use low-precision accumulators during inference without overflow.

AccFlow: Backward Accumulation for Long-Range Optical Flow

Guangyang Wu (University of Electronic Science and Technology of China), Wenyi Wang (University of Electronic Science and Technology of China)

CodeOptical FlowVideo

🎯 What it does: This paper proposes a recursive framework named AccFlow for estimating long-range optical flow by backward accumulating local optical flow.

Accurate and Fast Compressed Video Captioning

Yaojie Shen (Institute of Software, Chinese Academy of Sciences), Libo Zhang (Institute of Software, Chinese Academy of Sciences)

CodeGenerationCompressionComputational EfficiencyTransformerVideoText

🎯 What it does: Generate video subtitles directly in the compressed domain (I-frames, motion vectors, and residuals) in an end-to-end manner, eliminating the need to decode video frames or offline extract multimodal features.

Adaptive Calibrator Ensemble: Navigating Test Set Difficulty in Out-of-Distribution Scenarios

Yuli Zou (Hong Kong Polytechnic University), Liang Zheng (Australian National University)

CodeDomain AdaptationConvolutional Neural NetworkTransformerImage

🎯 What it does: This paper addresses the issue of model calibration failure on out-of-distribution (OOD) data by proposing a method based on Adaptive Calibrator Ensemble (ACE);

Adaptive Illumination Mapping for Shadow Detection in Raw Images

Jiayu Sun (Dalian University of Technology), Rynson Lau (City University of Hong Kong)

CodeObject DetectionSegmentationConvolutional Neural NetworkContrastive LearningImage

🎯 What it does: Using raw RAW images instead of traditional sRGB images for shadow detection, an Adaptive Illumination Mapping (AIM) module is proposed to generate sRGB images with different intensity ranges, and a feedback mechanism is employed to guide AIM in producing images with more shadow contrast, thereby improving shadow detection accuracy.

Adaptive Nonlinear Latent Transformation for Conditional Face Editing

Zhizhong Huang (Fudan University), Hongming Shan (Fudan University)

CodeImage TranslationGenerationFlow-based ModelGenerative Adversarial NetworkImage

🎯 What it does: Conditional editing of the latent space of StyleGAN is achieved through gradual nonlinear transformations for controllable modification of facial attributes.

Adaptive Rotated Convolution for Rotated Object Detection

Yifan Pu (Tsinghua University), Gao Huang (Tsinghua University)

CodeObject DetectionConvolutional Neural NetworkImage

🎯 What it does: An Adaptive Rotational Convolution (ARC) module is proposed, which can dynamically rotate convolution kernels according to the orientation of targets in different images, and enhance the feature representation capability of the backbone by combining multiple rotated kernels through a conditional computation mechanism.

Adaptive Similarity Bootstrapping for Self-Distillation Based Representation Learning

Tim Lebailly (KU Leuven), Tinne Tuytelaars (KU Leuven)

CodeKnowledge DistillationRepresentation LearningContrastive LearningImage

🎯 What it does: This paper focuses on the self-distillation framework in self-supervised representation learning, investigating the feasibility of using nearest neighbors (NN) to guide positive sample pairs, and proposes an adaptive similarity guidance method (AdaSim).

Adaptive Spiral Layers for Efficient 3D Representation Learning on Meshes

Francesca Babiloni (Huawei), Stefanos Zafeiriou (Imperial College London)

CodeComputational EfficiencyRepresentation LearningGraph Neural NetworkMesh

🎯 What it does: This paper proposes an adaptive spiral convolution layer suitable for 3D meshes, which can dynamically adjust the length and weights of the spiral path according to the mesh structure, thereby achieving efficient feature learning with a global receptive field and local refinement.

Adaptive Testing of Computer Vision Models

Irena Gao (Stanford University), Marco Tulio Ribeiro (Microsoft Research)

CodeClassificationObject DetectionRetrievalTransformerLarge Language ModelImageTextRetrieval-Augmented Generation

🎯 What it does: This paper presents AdaVision, a visual model testing process for human-computer interaction that helps users identify and fix semantically consistent failure modes of models.

Adding Conditional Control to Text-to-Image Diffusion Models

Lvmin Zhang (Stanford University), Maneesh Agrawala (Stanford University)

CodeGenerationData SynthesisConvolutional Neural NetworkDiffusion modelImage

🎯 What it does: Design and implement the ControlNet architecture, allowing users to finely control the spatial layout of generated images through additional conditional images (such as edge maps, pose skeletons, depth maps, etc.) without compromising the quality of the original large-scale pre-trained diffusion models (like Stable Diffusion).

Advancing Example Exploitation Can Alleviate Critical Challenges in Adversarial Training

Yao Ge (Nanjing University of Posts and Telecommunications), Xianzhong Long (Nanjing University of Posts and Telecommunications)

CodeAdversarial AttackConvolutional Neural NetworkImage

🎯 What it does: This paper studies example exploitation in adversarial training, first proposing a robust confidence metric that divides samples into accuracy-critical (A-C) and robustness-critical (R-C) categories, and analyzes their different contributions to model accuracy and robustness. Subsequently, a new example handling method is designed, which reduces the robustness learning intensity for A-C samples and enhances the robustness learning intensity for R-C samples (through adaptive λ or step size). This method is applied to both multi-step (TRADES, TEAT, etc.) and single-step (FastAT, GradAlign, etc.) adversarial training. Experiments show that it can simultaneously alleviate the accuracy-robustness trade-off, robustness overfitting, and catastrophic overfitting issues.

Advancing Referring Expression Segmentation Beyond Single Image

Yixuan Wu (Zhejiang University), Rui Zhao (SenseTime Research)

CodeObject DetectionSegmentationTransformerImageBenchmark

🎯 What it does: This paper proposes a Generalized Representation Segmentation (GRES) task for multi-image collections and constructs the corresponding GRD dataset and benchmark model GRSer.

Adversarial Bayesian Augmentation for Single-Source Domain Generalization

Sheng Cheng (Arizona State University), Yezhou Yang (University of Maryland Baltimore County)

CodeData SynthesisDomain AdaptationConvolutional Neural NetworkGenerative Adversarial NetworkImage

🎯 What it does: This paper proposes a new single-source domain generalization method called Adversarial Bayesian Augmentation (ABA), which enhances model performance in unknown domains by introducing Bayesian neural networks in convolutional layers and combining them with adversarial training to generate diverse image augmentations.

AGG-Net: Attention Guided Gated-Convolutional Network for Depth Image Completion

Dongyue Chen (Northeastern University), Tong Jia (Northeastern University)

CodeRestorationDepth EstimationConvolutional Neural NetworkImage

🎯 What it does: For RGB-D image depth completion, a novel Attention Guided Gated Convolution Network (AGG-Net) is proposed to achieve fine recovery of missing depth.

Agglomerative Transformer for Human-Object Interaction Detection

Danyang Tu (Shanghai Jiao Tong University), Wei Shen (Shanghai Jiao Tong University)

CodeRecognitionObject DetectionTransformerImage

🎯 What it does: A single-stage Transformer-based framework for person-object interaction detection, AGER, is proposed, which generates complete instance tokens internally in the encoder using text-guided dynamic clustering, thereby extracting complete instance-level features without the need for an additional object detector or instance decoder.

AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception

Dingkang Yang (Fudan University), Lihua Zhang (Fudan University)

CodeAutonomous DrivingConvolutional Neural NetworkTransformerVideoMultimodality

🎯 What it does: The AIDE driving perception dataset is proposed, and various baseline frameworks are constructed on this dataset, covering multi-view, multi-modal, and multi-task driving monitoring tasks.

All in Tokens: Unifying Output Space of Visual Tasks via Soft Token

Jia Ning (Huazhong University of Science and Technology), Han Hu (Huazhong University of Science and Technology)

CodeSegmentationPose EstimationDepth EstimationTransformerAuto EncoderImage

🎯 What it does: A unified framework for visual task output space, AiT, is proposed, which discretizes the high-dimensional outputs of different visual tasks into tokens and uses autoregressive Transformers for prediction, supporting various tasks such as depth estimation, instance segmentation, and keypoint detection.

All-to-Key Attention for Arbitrary Style Transfer

Mingrui Zhu (Xidian University), Xinbo Gao (Chongqing University of Post and Telecommunications)

CodeImage TranslationConvolutional Neural NetworkGenerative Adversarial NetworkContrastive LearningImage

🎯 What it does: A novel all-key attention (A2K) mechanism is proposed for efficient and stable arbitrary style transfer.

Among Us: Adversarially Robust Collaborative Perception by Consensus

Yiming Li (New York University), Chen Feng (New York University)

CodeObject DetectionAutonomous DrivingAdversarial AttackPoint Cloud

🎯 What it does: The ROBOSAC framework is proposed, utilizing the Random Sample Consensus (RANSAC) idea to achieve robustness against collaborative perception adversarial attacks;

An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferability

Bin Chen (Fuzhou University), Ximeng Liu (Fuzhou University)

CodeAdversarial AttackConvolutional Neural NetworkTransformerImage

🎯 What it does: This paper proposes AdaEA, which utilizes adaptive gradient modulation and a difference reduction filter to optimize multi-model ensemble attacks, enhancing the transferability of adversarial attacks between CNNs and ViTs.

An Embarrassingly Simple Backdoor Attack on Self-supervised Learning

Changjiang Li (Pennsylvania State University), Ting Wang (Pennsylvania State University)

CodeRepresentation LearningAdversarial AttackContrastive LearningImage

🎯 What it does: This paper proposes a self-supervised learning backdoor attack method named CTRL, which can implant a backdoor by contaminating a small amount of training data.

Anatomical Invariance Modeling and Semantic Alignment for Self-supervised Learning in 3D Medical Image Analysis

Yankai Jiang (Alibaba Group), Minfeng Xu (Alibaba Group)

CodeSegmentationRepresentation LearningTransformerContrastive LearningImageBiomedical DataComputed Tomography

🎯 What it does: This paper proposes a self-supervised learning framework called Alice, which utilizes cross-volume sampling to obtain positive samples of the same anatomical structure and performs semantic alignment within the same volume, thereby explicitly modeling anatomically invariant features.

Anomaly Detection Under Distribution Shift

Tri Cao (Singapore Management University), Guansong Pang (Singapore Management University)

CodeAnomaly DetectionKnowledge DistillationImageBenchmark

🎯 What it does: An unsupervised anomaly detection method called GNL is proposed for scenarios with distribution shifts, and benchmarks are established on four commonly used datasets.

Anti-DreamBooth: Protecting Users from Personalized Text-to-image Synthesis

Thanh Van Le (VinAI Research), Anh Tran (VinAI Research)

CodeGenerationSafty and PrivacyAdversarial AttackDiffusion modelImage

🎯 What it does: In response to the potential misuse of the DreamBooth personalized text-image model, this paper proposes Anti-DreamBooth, which adds nearly invisible perturbations before users upload images, resulting in poor quality or distorted personalized images generated by any DreamBooth fine-tuning model trained on these images, thereby protecting user privacy.

Aperture Diffraction for Compact Snapshot Spectral Imaging

Tao Lv (Nanjing University), Xun Cao (Nanjing University)

CodeRestorationTransformerImage

🎯 What it does: A compact snapshot spectral imaging system ADIS, composed solely of an ultra-thin orthogonal aperture mask and a standard imaging lens, has been designed, and a spectral reconstruction algorithm CSST based on this system has been proposed.

AREA: Adaptive Reweighting via Effective Area for Long-Tailed Classification

Xiaohua Chen (Institute of Information Engineering), Weiping Wang (Institute of Information Engineering)

CodeClassificationImage

🎯 What it does: The AREA (Adaptive Reweighting via Effective Area) method is proposed, which improves the class imbalance problem in long-tail classification tasks by calculating the effective area for each category to achieve adaptive reweighting.

ARNOLD: A Benchmark for Language-Grounded Task Learning with Continuous States in Realistic 3D Scenes

Ran Gong (University of California), Siyuan Huang (National Key Laboratory of General Artificial Intelligence)

CodeRobotic IntelligenceReinforcement LearningImageVideoBenchmark

🎯 What it does: The ARNOLD benchmark has been constructed, which includes 8 language-driven robotic tasks aimed at continuous states, providing real 3D scenes, multi-camera observations, 10k expert demonstrations, and various generalization data splits; a systematic evaluation of language and state understanding has also been implemented.

Atmospheric Transmission and Thermal Inertia Induced Blind Road Segmentation with a Large-Scale Dataset TBRSD

Junzhang Chen (Beihang University), Xiangzhi Bai (Beihang University)

CodeObject DetectionSegmentationTransformerImage

🎯 What it does: This paper proposes a blind road semantic segmentation network based on thermal infrared images, and for the first time introduces two physical models, atmospheric transmission and thermal inertia effects, into the network, improving the accuracy of blind road detection in low-light environments.

Attentive Mask CLIP

Yifan Yang (Microsoft Research), Yuqing Yang (Microsoft Research)

CodeClassificationRetrievalComputational EfficiencyTransformerContrastive LearningImage

🎯 What it does: An efficient CLIP pre-training framework A-CLIP is constructed through attention-driven sparse cropping of image tokens.

AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism

Chongyang Zhong (Institute of Computing Technology Chinese Academy of Sciences), Shihong Xia (Institute of Computing Technology Chinese Academy of Sciences)

CodeGenerationData SynthesisTransformerAuto EncoderVideoTextMultimodality

🎯 What it does: This paper proposes AttT2M, a two-stage multi-view attention mechanism for text-driven human action generation. The first stage utilizes a spatiotemporal encoder with body part attention and VQ-VAE to learn a discrete latent space; the second stage captures the cross-modal correspondence between text and actions through global-local attention (sentence-level conditional self-attention + word-level cross-attention) and generates action sequences using a generative Transformer.

Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection

Yuyang Liu (Chinese Academy of Sciences), Joost van de Weijer (University Autonoma de Barcelona)

CodeObject DetectionKnowledge DistillationConvolutional Neural NetworkImage

🎯 What it does: This paper addresses the foreground drift problem in incremental object detection and proposes solutions including Augmented Box Replay (ABR) and Attentive RoI Distillation.

Augmenting and Aligning Snippets for Few-Shot Video Domain Adaptation

Yuecong Xu (Institute for Infocomm Research), Xiaoli Li (Institute for Infocomm Research)

CodeRecognitionDomain AdaptationTransformerVideo

🎯 What it does: A new method called SSA2lign is proposed to address the problem of video domain adaptation with only a small number of target video samples.

Automated Knowledge Distillation via Monte Carlo Tree Search

Lujun Li (Hong Kong University of Science and Technology), Ya Yang (City University of Hong Kong)

CodeClassificationObject DetectionSegmentationKnowledge DistillationTransformerImage

🎯 What it does: Proposes Auto-KD, which automates the design of knowledge distillation for the first time, constructing a unified tree search space and using Monte Carlo Tree Search for efficient searching;

Automatic Network Pruning via Hilbert-Schmidt Independence Criterion Lasso under Information Bottleneck Principle

Song Guo (Xiamen University), Rongrong Ji (Xiamen University)

CodeCompressionOptimizationConvolutional Neural NetworkImage

🎯 What it does: This paper proposes an automatic channel pruning method called APIB based on the Information Bottleneck (IB) principle, which uses HSIC Lasso to solve the IB approximation and automatically determines the pruning ratio for each layer.

AutoReP: Automatic ReLU Replacement for Fast Private Network Inference

Hongwu Peng (University of Connecticut), Caiwen Ding (University of Connecticut)

CodeSafty and PrivacyComputational EfficiencyConvolutional Neural NetworkImage

🎯 What it does: We propose AutoReP, an automatic ReLU replacement framework for private inference that significantly reduces ReLU operations while maintaining high accuracy.

BANSAC: A Dynamic BAyesian Network for Adaptive SAmple Consensus

Valter Piedade (Instituto Superior Tecnico), Pedro Miraldo (Mitsubishi Electric Research Labs)

CodePose EstimationOptimizationComputational EfficiencyReinforcement LearningImage

🎯 What it does: This paper proposes BANSAC, a variant of RANSAC that utilizes dynamic Bayesian networks to dynamically update the inlier probabilities of each matching point and performs probability-weighted sampling; it also provides a probability-based termination criterion.

Bayesian Optimization Meets Self-Distillation

HyunJae Lee (Lunit Inc), Donggeun Yoo (Lunit Inc)

CodeClassificationOptimizationKnowledge DistillationConvolutional Neural NetworkImageBiomedical Data

🎯 What it does: By combining Bayesian optimization with self-distillation, the BOSS framework is proposed to utilize the parameters and performance knowledge of previously trained models in each BO iteration to enhance the final model performance.

Bayesian Prompt Learning for Image-Language Model Generalization

Mohammad Mahdi Derakhshani (University of Amsterdam), Brais Martinez (Samsung AI Cambridge)

CodeClassificationDomain AdaptationTransformerPrompt EngineeringVision Language ModelImageText

🎯 What it does: By viewing prompt learning as Bayesian variational inference, a Bayesian prompt learning method is proposed to regularize the prompt space and enhance the generalization ability of unseen prompts.

Beating Backdoor Attack at Its Own Game

Min Liu (Carnegie Mellon University), Xiangyu Yue (Chinese University of Hong Kong)

CodeAnomaly DetectionAdversarial AttackConvolutional Neural NetworkImage

🎯 What it does: This paper proposes a Non-Adversarial Backdoor (NAB) framework that defends against backdoor attacks by injecting non-adversarial backdoors into a small number of suspected samples to suppress original backdoor attacks.

Better May Not Be Fairer: A Study on Subgroup Discrepancy in Image Classification

Ming-Chang Chiu (University of Southern California), Xuezhe Ma (University of Southern California)

CodeClassificationData-Centric LearningConvolutional Neural NetworkFlow-based ModelImage

🎯 What it does: Manually annotated the CIFAR-10/100 test set based on background color to generate the CIFAR-B dataset, studied subgroup performance differences, and proposed the FlowAug semantic data augmentation method to reduce subgroup differences.

BEVPlace: Learning LiDAR-based Place Recognition using Bird's Eye View Images

Lun Luo (Zhejiang University), Hui-Liang Shen (Zhejiang University)

CodeRecognitionPose EstimationAutonomous DrivingConvolutional Neural NetworkSimultaneous Localization and MappingPoint CloudBenchmark

🎯 What it does: The study uses Bird's Eye View (BEV) as a representation of LiDAR point clouds and proposes a rotation-invariant network called BEVPlace based on group convolution and NetVLAD for place recognition and location estimation of point clouds.

Beyond One-to-One: Rethinking the Referring Image Segmentation

Yutao Hu (University of Hong Kong), Ping Luo (University of Hong Kong)

CodeSegmentationTransformerContrastive LearningImageTextMultimodality

🎯 What it does: A Dual Multi-Modal Interaction (DMMI) network is proposed to address the segmentation difficulties when natural language descriptions point to multiple targets or no targets.

Beyond Skin Tone: A Multidimensional Measure of Apparent Skin Color

William Thong (Sony AI), Alice Xiang (Sony AI)

CodeRecognitionSegmentationGenerationGenerative Adversarial NetworkImage

🎯 What it does: Proposes and evaluates a multidimensional skin color measurement method based on the CIELAB color space (L* represents skin color depth, h* represents skin color hue), and uses this method to detect skin color bias in image datasets and computer vision models.

Bidirectional Alignment for Domain Adaptive Detection with Transformers

Liqiang He (Oregon State University), Sinisa Todorovic (Oregon State University)

CodeObject DetectionDomain AdaptationTransformerImage

🎯 What it does: A cross-domain object detection method named BiADT is proposed, which separates domain-invariant and domain-specific features for each token in the encoder and decoder of the Transformer, and achieves alignment of domain-invariant features and distinction of domain-specific features through bidirectional alignment.

Bird's-Eye-View Scene Graph for Vision-Language Navigation

Rui Liu (Zhejiang University), Yi Yang (Zhejiang University)

CodeObject DetectionRobotic IntelligenceTransformerVision Language ModelMultimodalityPoint Cloud

🎯 What it does: By constructing a scene graph based on Bird's Eye View (BEV), this paper achieves three-dimensional perception of indoor environments and utilizes the scene graph for visual-language navigation decision-making.

Black Box Few-Shot Adaptation for Vision-Language Models

Yassine Ouali (Samsung AI), Georgios Tzimiropoulos (Queen Mary University of London)

CodeDomain AdaptationPrompt EngineeringVision Language ModelImage

🎯 What it does: This paper proposes a novel black-box few-shot visual-language model adaptation method called LFA, which achieves cross-domain adaptation using only pre-computed image and text features without accessing model weights.

Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive Collaboration

Xinghao Wu (Beihang University), Shaojie Tang (University of Texas at Dallas)

CodeFederated LearningImage

🎯 What it does: This paper proposes a personalized federated learning framework called FedCAC, which is based on parameter sensitivity and client data distribution similarity, enabling better collaboration and personalization among clients in non-IID scenarios.

BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification

Yuanhong Chen (Australian Institute for Machine Learning, University of Adelaide), Gustavo Carneiro (Centre for Vision, Speech and Signal Processing, University of Surrey)

CodeClassificationConvolutional Neural NetworkLarge Language ModelImageBiomedical DataBenchmark

🎯 What it does: A two-stage method for handling noisy multi-label chest X-ray image classification is proposedβ€”Bag of Multi-Label Descriptors (BoMD).

Boosting Adversarial Transferability via Gradient Relevance Attack

Hegui Zhu (Northeastern University), Wuming Jiang (Beijing EyeCool Technology)

CodeAdversarial AttackImage

🎯 What it does: This paper proposes the Gradient Relevance Attack (GRA), which enhances the transferability of adversarial samples through a gradient relevance framework and decay indicators.

Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching

Jiazheng Xing (Zhejiang University), Yong Liu (Zhejiang University)

CodeRecognitionGraph Neural NetworkVideo

🎯 What it does: A graph-guided hybrid matching framework (GgHM) is proposed for few-shot action recognition.

Boosting Positive Segments for Weakly-Supervised Audio-Visual Video Parsing

Kranthi Kumar Rachavarapu (Indian Institute of Technology Madras), Rajagopalan A. N. (Indian Institute of Technology Madras)

CodeClassificationRecognitionSegmentationVideoMultimodalityAudio

🎯 What it does: This paper proposes a weakly supervised audio-video event parsing framework based on the Poisson-Binomial distribution, which improves the detection rate of positive sample segments through EM iteration, significantly enhancing event localization performance.

Boosting Single Image Super-Resolution via Partial Channel Shifting

Xiaoming Zhang (Southwest Jiaotong University), Xiaole Zhao (Southwest Jiaotong University)

CodeRestorationSuper ResolutionConvolutional Neural NetworkImage

🎯 What it does: This paper studies a feature enhancement method without additional parameters or computational overheadβ€”Partial Channel Shifting (PCS)β€”to improve the performance of single-image super-resolution models.

Boosting Whole Slide Image Classification from the Perspectives of Distribution, Correlation and Magnification

Linhao Qu (Fudan University), Zhijian Song (Fudan University)

CodeClassificationTransformerContrastive LearningImage

🎯 What it does: A multi-scale multi-stage MIL framework called MILBooster is proposed for WSI classification.

Borrowing Knowledge From Pre-trained Language Model: A New Data-efficient Visual Learning Paradigm

Wenxuan Ma (Beijing Institute of Technology), Gao Huang (Tsinghua University)

CodeClassificationDomain AdaptationData-Centric LearningTransformerLarge Language ModelContrastive LearningImageText

🎯 What it does: This paper proposes a method called BorLan that utilizes knowledge from pre-trained language models to enhance the learning efficiency of visual models in data-scarce tasks.

Box-based Refinement for Weakly Supervised and Unsupervised Localization Tasks

Eyal Gomel (Tel Aviv University), Lior Wolf (Tel Aviv University)

CodeRecognitionObject DetectionTransformerContrastive LearningImageMultimodality

🎯 What it does: By training a detector on the outputs of original localization networks (such as DINO and CLIP visual encoders) and using the bounding boxes generated by the detector to refine the original network, improvements in localization are achieved under unsupervised and weakly supervised conditions.

BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion

Jinheng Xie (National University of Singapore), Mike Zheng Shou (National University of Singapore)

CodeGenerationData SynthesisDiffusion modelImageText

🎯 What it does: A training-free method named BoxDiff is proposed for synthesizing images based on spatial conditions provided by users (such as boxes or doodles).

BoxSnake: Polygonal Instance Segmentation with Box Supervision

Rui Yang (Tsinghua University), Xiu Li (Tsinghua University)

CodeObject DetectionSegmentationTransformerImage

🎯 What it does: A BoxSnake method is proposed, which achieves end-to-end polygon instance segmentation using only box annotations;

Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Models

Hee-Seon Kim (Korea Advanced Institute of Science and Technology), Changick Kim (Korea Advanced Institute of Science and Technology)

CodeAdversarial AttackConvolutional Neural NetworkImageVideo

🎯 What it does: This paper proposes a framework for generating universal adversarial perturbations for videos based on image models and image data (BTC-UAP), utilizing image classification models for adversarial optimization on each frame, and attacking video models by minimizing the feature similarity between adjacent frames.

Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection

Longrong Yang (Zhejiang University), Xi Li (Zhejiang University)

CodeObject DetectionKnowledge DistillationImage

🎯 What it does: A knowledge distillation framework for dense object detection is proposed to address the issue of inconsistent cross-task protocols, with a binary classification distillation loss and an IoU localization distillation loss designed separately.

Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation

Zunnan Xu (Sun Yat-sen University), Guanbin Li (Sun Yat-sen University)

CodeObject DetectionSegmentationTransformerVision Language ModelContrastive LearningImageMultimodality

🎯 What it does: This study proposes a parameter-efficient tuning framework based on a dual-stream vision-language modelβ€”Bridgerβ€”for reference image segmentation tasks.

Bring Clipart to Life

Nanxuan Zhao (Adobe Research), Nan Cao (Tongji University)

CodeImage TranslationGenerationDomain AdaptationGenerative Adversarial NetworkContrastive LearningImage

🎯 What it does: ClipFaceShop proposes a clipart-based facial photo editing method that can accurately transfer abstract clipart facial attributes (such as hairstyle, expression, beard, etc.) to real photos while maintaining the identity of the portrait.

BT^2: Backward-compatible Training with Basis Transformation

Yifei Zhou (University of California), Ser-Nam Lim (Meta AI)

CodeClassificationRepresentation LearningConvolutional Neural NetworkTransformerContrastive LearningImageMultimodality

🎯 What it does: The BT 2 method is proposed, which adds necessary dimensions through learnable basis transformations in backward-compatible training, maintaining the performance of the new model while being compatible with the old model.

CAD-Estate: Large-scale CAD Model Annotation in RGB Videos

Kevis-Kokitsi Maninis (Google Research), Vittorio Ferrari (Google Research)

CodeObject DetectionObject TrackingPose EstimationRetrievalOptimizationSimultaneous Localization and MappingVideoMesh

🎯 What it does: This paper proposes a semi-automated workflow that combines RGB videos with a CAD model database to generate globally consistent 9-DoF CAD model pose annotations for multi-object scenes in videos, constructing the CAD-Estate dataset with a scale of 20k videos, 101k instances, and 12k independent CAD models.

Cascade-DETR: Delving into High-Quality Universal Object Detection

Mingqiao Ye (ETH Zurich), Fisher Yu (ETH Zurich)

CodeObject DetectionDomain AdaptationTransformerImageBenchmark

🎯 What it does: This paper proposes Cascade-DETR, a model that achieves high-quality cross-domain object detection through cascaded attention and IoU prediction recalibration based on DETR.

CASSPR: Cross Attention Single Scan Place Recognition

Yan Xia (Technical University of Munich), Daniel Cremers (Technical University of Munich)

CodeRecognitionRetrievalTransformerSimultaneous Localization and MappingPoint Cloud

🎯 What it does: This paper proposes CASSPR, a cross-attention transformer that combines point clouds and sparse voxels for scene recognition from single-frame LiDAR point clouds.

CauSSL: Causality-inspired Semi-supervised Learning for Medical Image Segmentation

Juzheng Miao (Chinese University of Hong Kong), Pheng-Ann Heng (Chinese University of Hong Kong)

CodeSegmentationConvolutional Neural NetworkImageBiomedical DataComputed Tomography

🎯 What it does: A semi-supervised segmentation method for medical imaging based on causal graphs, CauSSL, is proposed, which enhances model performance through algorithm independence.

CBA: Improving Online Continual Learning via Continual Bias Adaptor

Quanziang Wang (Xi'an Jiaotong University), Deyu Meng (Macau University of Science and Technology)

CodeClassificationOptimizationConvolutional Neural NetworkSupervised Fine-TuningImage

🎯 What it does: The Continual Bias Adaptor (CBA) module is proposed, which dynamically compensates for catastrophic distribution drift through augmented classifiers and dual-layer optimization in online continual learning, thereby alleviating forgetting.

CDFSL-V: Cross-Domain Few-Shot Learning for Videos

Sarinda Samarasinghe (University of Central Florida), Mubarak Shah (University of Central Florida)

CodeClassificationRecognitionDomain AdaptationAuto EncoderContrastive LearningVideo

🎯 What it does: A cross-domain few-shot video action recognition method is proposed, which achieves feature balance between the source domain and the target domain by combining self-supervised pre-training and curriculum learning.

Center-Based Decoupled Point-cloud Registration for 6D Object Pose Estimation

Haobo Jiang (Nanjing University of Science and Technology), Jian Yang (Nanjing University of Science and Technology)

CodePose EstimationConvolutional Neural NetworkPoint Cloud

🎯 What it does: A decoupled point cloud registration framework based on object centers is proposed, estimating translation through center regression and predicting rotation using center-aligned point clouds, achieving 6D object pose estimation.

CGBA: Curvature-aware Geometric Black-box Attack

Md Farhamdur Reza (North Carolina State University), Huaiyu Dai (North Carolina State University)

CodeAdversarial AttackConvolutional Neural NetworkTransformerGaussian SplattingImage

🎯 What it does: Two decision boundary black-box attack methods, CGBA and CGBA-H, are proposed. They efficiently generate adversarial samples with a low query budget by searching for decision boundary points along a semicircular trajectory on a two-dimensional constrained plane, and provide a better initial boundary point selection scheme.

Chaotic World: A Large and Challenging Benchmark for Human Behavior Understanding in Chaotic Events

Kian Eng Ong (Singapore University of Technology and Design), Jun Liu (Singapore University of Technology and Design)

CodeRecognitionObject DetectionSegmentationVideoTextMultimodalityBenchmarkAudio

🎯 What it does: The first large-scale multimodal dataset, Chaotic World, has been constructed to analyze human behavior in chaotic events, and a unified multitask model, IntelliCare, has been proposed.

ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules

Zhi-Qi Cheng (Carnegie Mellon University), Alexander G. Hauptmann (Carnegie Mellon University)

CodeTransformerVision Language ModelTabular

🎯 What it does: A unified framework called ChartReader is proposed, integrating three major tasks: chart rendering (Chart-to-Table) and chart understanding (ChartQA, Chart-to-Text), forming an end-to-end unstructured learning process.

Chasing Clouds: Differentiable Volumetric Rasterisation of Point Clouds as a Highly Efficient and Accurate Loss for Large-Scale Deformable 3D Registration

Mattias P. Heinrich (University of Luebeck), Lasse Hansen (EchoScout GmbH)

CodeOptimizationGraph Neural NetworkPoint CloudComputed Tomography

🎯 What it does: Unsupervised and self-supervised registration of highly deformable 3D point clouds is performed, proposing a differentiable voxel rasterization loss that addresses the gradient sparsity and non-differentiability issues of traditional Chamfer/EMD in high-resolution and complex geometries.

Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning

Haiyang Yu (Fudan University), Xiangyang Xue (Fudan University)

CodeRecognitionTransformerContrastive LearningImageText

🎯 What it does: A two-stage framework is designed: first, a CLIP pre-trained model aligned with printed character images and Chinese character IDS is used to learn the normative representation of Chinese characters, and then this representation is applied to a text recognition model to achieve zero-shot recognition of Chinese text.

CIRI: Curricular Inactivation for Residue-aware One-shot Video Inpainting

Weiying Zheng (South China University of Technology), Shengfeng He (Singapore Management University)

CodeRestorationSegmentationVideo

🎯 What it does: This study investigates a one-shot video inpainting framework that converts traditional video inpainting models to single annotation (only the first frame mask), addressing the problem of filling in missing areas in dynamic scenes.

CiT: Curation in Training for Effective Vision-Language Data

Hu Xu (Meta AI), Christoph Feichtenhofer (Meta AI)

CodeComputational EfficiencyRepresentation LearningData-Centric LearningTransformerVision Language ModelContrastive LearningImageTextMultimodality

🎯 What it does: This paper proposes an algorithm for dynamic data selection during the training processβ€”CiT (Curation in Training). By utilizing a pre-trained text encoder, it matches the metadata of the target task with a vast number of image-text pairs for similarity, thereby automatically filtering out more relevant data in the training loop, significantly improving data utilization efficiency.

Class-Aware Patch Embedding Adaptation for Few-Shot Image Classification

Fusheng Hao (Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences), Jun Cheng (Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences)

CodeClassificationRepresentation LearningTransformerSupervised Fine-TuningImage

🎯 What it does: In few-shot image classification, image representation and similarity computation are improved by making the patch embeddings of ViT category-related and defining a dense similarity matrix.

Class-incremental Continual Learning for Instance Segmentation with Image-level Weak Supervision

Yu-Hsing Hsieh (National Taiwan University), Chu-Song Chen (National Taiwan University)

CodeObject DetectionSegmentationKnowledge DistillationConvolutional Neural NetworkImage

🎯 What it does: A class-incremental continual learning instance segmentation framework CL4WSIS based on image-level weak labels has been developed, which can gradually learn new categories while maintaining instance segmentation capabilities for old categories using only image labels.

Class-Incremental Grouping Network for Continual Audio-Visual Learning

Shentong Mo (Carnegie Mellon University), Yapeng Tian (University of Texas at Dallas)

CodeKnowledge DistillationRepresentation LearningConvolutional Neural NetworkTransformerMultimodalityAudio

🎯 What it does: A continuous learning framework named Class-Incremental Grouping Network (CIGN) is proposed for category-level semantic representation learning of audio and visual inputs in a multi-task environment, achieving audio-visual source classification.

CLIP-Cluster: CLIP-Guided Attribute Hallucination for Face Clustering

Shuai Shen (Tsinghua University), Jiwen Lu (Tsinghua University)

CodeClassificationRecognitionGraph Neural NetworkTransformerContrastive LearningImage

🎯 What it does: This paper proposes a CLIP-based attribute hallucination framework (CLIP-Cluster) that generates features corresponding to various attributes (age, pose, expression) guided by text, and utilizes a neighbor-aware generative model to fuse these features to reduce attribute differences within the same identity, thereby achieving more compact facial clustering.

CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection

Jie Liu (City University of Hong Kong), Zongwei Zhou (Johns Hopkins University)

CodeObject DetectionSegmentationConvolutional Neural NetworkVision Language ModelContrastive LearningImageBiomedical DataComputed Tomography

🎯 What it does: A general model based on CLIP has been proposed and trained, capable of segmenting and detecting 25 organs and 6 types of tumors across various abdominal CT datasets, and it can handle partially annotated data.

CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-Training

Tianyu Huang (Harbin Institute of Technology), Wangmeng Zuo (Harbin Institute of Technology)

CodeClassificationContrastive LearningImagePoint Cloud

🎯 What it does: The CLIP2Point method is proposed, utilizing image-depth contrastive learning to pre-train a deep encoder, transferring CLIP's visual-text knowledge to 3D point cloud classification tasks.

CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No

Hualiang Wang (Hong Kong University of Science and Technology), Xiaomeng Li (Hong Kong University of Science and Technology)

CodeClassificationAnomaly DetectionTransformerPrompt EngineeringContrastive LearningImage

🎯 What it does: Proposes the CLIPN method, injecting the 'negation' logic of CLIP into zero-shot OOD detection;

CLIPTER: Looking at the Bigger Picture in Scene Text Recognition

Aviad Aberdam (Amazon Web Services), Ron Litman (Amazon Web Services)

CodeRecognitionTransformerVision Language ModelImage

🎯 What it does: This paper proposes the CLIPTER framework, which integrates global scene context into existing scene text recognizers by merging image-level features extracted from frozen vision-language models (such as CLIP/BLIP) with local features of cropped text images through gated cross-attention.