arXivSub Start free trial

CVPR 2023 Papers with Code β€” Page 8

IEEE/CVF Conference on Computer Vision and Pattern Recognition Β· 830 papers

Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation

Lingting Zhu (University of Hong Kong), Lequan Yu (University of Hong Kong)

CodeGenerationData SynthesisPose EstimationTransformerDiffusion modelMultimodalityTime SeriesAudio

🎯 What it does: This paper proposes a framework for audio-driven co-speech gesture generation based on diffusion models, called DiffGesture, which can generate highly relevant and temporally coherent full-body pose sequences without using text or speaker identity.

Tangentially Elongated Gaussian Belief Propagation for Event-Based Incremental Optical Flow Estimation

Jun Nagata (DENSO IT LAB INC), Yusuke Sekikawa (DENSO IT LAB INC)

CodeAutonomous DrivingOptical FlowImageVideo

🎯 What it does: This paper proposes an incremental full optical flow estimation method TEGBP based on event cameras, which infers complete optical flow from sparse normal flow.

TAPS3D: Text-Guided 3D Textured Shape Generation From Pseudo Supervision

Jiacheng Wei (Nanyang Technological University), Kim-Hui Yap (Nanyang Technological University)

CodeGenerationData SynthesisVision Language ModelGenerative Adversarial NetworkPoint CloudMesh

🎯 What it does: A 3D texture shape generation model named TAPS3D was trained, capable of generating high-quality, controllable three-dimensional objects in one go based on given text prompts.

TarViS: A Unified Approach for Target-Based Video Segmentation

Ali Athar (RWTH Aachen University), Bastian Leibe (RWTH Aachen University)

CodeObject TrackingSegmentationTransformerVideo

🎯 What it does: This paper proposes TarViS, a unified Transformer-based network that can perform video instance segmentation, video panoptic segmentation, video object segmentation, and point tracking within the same model.

Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning

Wenjin Wang (Zhejiang University), Yin Zhang (Zhejiang University)

CodeKnowledge DistillationNeural Architecture SearchMixture of ExpertsImage

🎯 What it does: A lifelong learning framework called PAR is proposed, which can dynamically select parameter allocation or parameter regularization strategies based on the learning difficulty of tasks.

Task Residual for Tuning Vision-Language Models

Tao Yu (National University of Singapore), Xinchao Wang (National University of Singapore)

CodeClassificationDomain AdaptationTransformerVision Language ModelContrastive LearningImageMultimodality

🎯 What it does: Proposes Task Residual Tuning (TaskRes), which adds learnable residual parameters to the CLIP pre-trained text classifier while keeping it unchanged to achieve efficient transfer learning.

Task-Specific Fine-Tuning via Variational Information Bottleneck for Weakly-Supervised Pathology Whole Slide Image Classification

Honglin Li (Zhejiang University), Lin Yang (Westlake University)

CodeClassificationDomain AdaptationComputational EfficiencyTransformerContrastive LearningImageBiomedical Data

🎯 What it does: A task-specific fine-tuning framework based on information bottleneck is proposed, which significantly improves weakly supervised whole slide image classification performance by utilizing multi-instance learning and SSL pre-trained features.

TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving

Shaoheng Fang (Shanghai Jiao Tong University), Siheng Chen (Shanghai Jiao Tong University)

CodeObject DetectionSegmentationAutonomous DrivingTransformerImageVideo

🎯 What it does: This paper proposes a vision-based joint perception and prediction framework called TBP-Former, which utilizes a PoseSync BEV encoder and a spatial-temporal pyramid Transformer to detect, segment, and predict future trajectories of targets such as vehicles and pedestrians in synchronized BEV space.

Teaching Structured Vision & Language Concepts to Vision & Language Models

Sivan Doveh (IBM Research), Leonid Karlinsky (MIT-IBM Watson AI Lab)

CodeClassificationData-Centric LearningTransformerLarge Language ModelSupervised Fine-TuningVision Language ModelContrastive LearningTextMultimodality

🎯 What it does: By processing the existing visual-text pair data, structured visual-language concept (SVLC) positive and negative samples are generated using methods such as rules, LLM, and analogy, supplemented by additional loss training to enhance the VL model's understanding of object attributes, relationships, and states of SVLC.

Tell Me What Happened: Unifying Text-Guided Video Completion via Multimodal Masked Video Generation

Tsu-Jui Fu (University of California Santa Barbara), Sean Bell (Meta)

CodeGenerationData SynthesisTransformerGenerative Adversarial NetworkContrastive LearningVideoTextMultimodality

🎯 What it does: This paper proposes the Text-Guided Video Completion (TVC) task, which can generate complete video sequences based on given starting frames, ending frames, or frames from both ends, along with natural language descriptions.

Temporal Consistent 3D LiDAR Representation Learning for Semantic Perception in Autonomous Driving

Lucas Nunes (University of Bonn), Cyrill Stachniss (University of Bonn)

CodeObject DetectionSegmentationAutonomous DrivingRepresentation LearningTransformerContrastive LearningPoint Cloud

🎯 What it does: This paper proposes a method for self-supervised representation learning that utilizes vehicle motion to obtain LiDAR views of the same object at different times, training the network to learn time-consistent and robust point cloud features against object dynamics.

TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation

Devavrat Tomar (EPFL), Jean-Philippe Thiran (EPFL)

CodeDomain AdaptationKnowledge DistillationContrastive LearningImageBiomedical DataMagnetic Resonance Imaging

🎯 What it does: A self-learning method called TeSLA is proposed, which utilizes automatic adversarial augmentation for online adaptation of pre-trained models on unlabeled streaming test data.

Text With Knowledge Graph Augmented Transformer for Video Captioning

Xin Gu (University of Chinese Academy of Sciences), Longyin Wen (ByteDance Inc.)

CodeGenerationTransformerVideoText

🎯 What it does: This paper proposes TextKG, a dual-stream Transformer model enhanced by knowledge graphs, aimed at generating more accurate video subtitles.

Texts as Images in Prompt Tuning for Multi-Label Image Recognition

Zixian Guo (Harbin Institute of Technology), Wangmeng Zuo (Harbin Institute of Technology)

CodeClassificationRecognitionPrompt EngineeringVision Language ModelImageText

🎯 What it does: This paper proposes treating text descriptions as images for prompt tuning (TaI prompting) and introduces dual-granularity prompt tuning (TaI-DPT) in multi-label image recognition to simultaneously leverage global and local features.

The Best Defense Is a Good Offense: Adversarial Augmentation Against Adversarial Attacks

Iuri Frosio (NVIDIA), Jan Kautz (NVIDIA)

CodeAdversarial AttackConvolutional Neural NetworkImage

🎯 What it does: A new framework A5 (Adversarial Augmentation to Defend Against Adversarial Attacks) is proposed, which is the first certified preventive defense method against adversarial attacks, aimed at ensuring that any attack will fail by constructing defensive perturbations.

The Dark Side of Dynamic Routing Neural Networks: Towards Efficiency Backdoor Injection

Simin Chen (University of Texas at Dallas), Wei Yang (University of Texas at Dallas)

CodeComputational EfficiencyAdversarial AttackConvolutional Neural NetworkImage

🎯 What it does: This paper studies and implements an attack method called EfficFrog that can implant an 'efficiency backdoor' in dynamic neural networks. The attacker can cause the victim model to consume more computational resources when triggered by specific inputs using a small amount of training data, leading to a decrease in system availability.

The Devil Is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation

Beomyoung Kim (NAVER Cloud), Sung Ju Hwang (NAVER AI Lab)

CodeObject DetectionSegmentationAutonomous DrivingConvolutional Neural NetworkSupervised Fine-TuningImage

🎯 What it does: This paper proposes a Weakly Supervised Instance Segmentation (WSSIS) framework that utilizes point labels with just one pixel as a weak supervision source and refines coarse masks using MaskRefineNet.

The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training

Gi-Cheon Kang (Seoul National University), Byoung-Tak Zhang (Seoul National University)

CodeGenerationData SynthesisRetrievalTransformerVision Language ModelGenerative Adversarial NetworkImageMultimodality

🎯 What it does: Proposes Generative Self-Training (GST) to expand the VisDial training set by generating multi-turn visual dialogue data on unlabeled images from the web.

Thermal Spread Functions (TSF): Physics-Guided Material Classification

Aniket Dashpute (Rice University), Oliver Cossairt (University of Arizona)

CodeClassificationRecognitionImagePhysics Related

🎯 What it does: Using low-power laser heating and recording the thermal diffusion process of objects with a thermal camera, the thermal diffusion function (TSF) is extracted. By solving the inverse heat conduction equation, the thermal diffusivity and emissivity are obtained, which are then used as features for material classification, ultimately achieving an accuracy of about 86% in multi-class recognition.

Think Twice Before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving

Xiaosong Jia (Shanghai Jiao Tong University), Hongyang Li (Shanghai AI Laboratory)

CodeAutonomous DrivingKnowledge DistillationRecurrent Neural NetworkTransformerReinforcement LearningMultimodalityPoint Cloud

🎯 What it does: This paper proposes the ThinkTwice end-to-end autonomous driving framework, which implements a scalable decision network through a multi-layer coarse-to-fine prediction decoder (Look, Predict, Refine).

TINC: Tree-Structured Implicit Neural Compression

Runzhao Yang (Tsinghua University)

CodeCompressionBiomedical DataComputed Tomography

🎯 What it does: Proposes the Tree-structured Implicit Neural Compression (TINC) framework, which first divides large-scale data into blocks and uses MLP for local INR representation, then shares parameters in a tree hierarchical structure to enhance compression quality.

TinyMIM: An Empirical Study of Distilling MIM Pre-Trained Models

Sucheng Ren (Microsoft Research Asia), Han Hu (Microsoft Research Asia)

CodeClassificationSegmentationKnowledge DistillationTransformerImage

🎯 What it does: Knowledge is transferred from a large-scale Masked Image Modeling (MIM) pre-trained model to a small Vision Transformer (ViT) through knowledge distillation, thereby enhancing the performance of the small model.

TIPI: Test Time Adaptation With Transformation Invariance

A. Tuan Nguyen (University of Oxford), Philip H.S. Torr (University of Oxford)

CodeClassificationDomain AdaptationAdversarial AttackImage

🎯 What it does: During the inference phase, online adaptation for the pre-trained model is performed, proposing an unsupervised input transformation invariance regularization objective to prevent model collapse under small batch sizes.

Token Contrast for Weakly-Supervised Semantic Segmentation

Lixiang Ru (Wuhan University), Bo Du (Wuhan University)

CodeSegmentationTransformerContrastive LearningImage

🎯 What it does: By designing two contrastive modules, Patch Token Contrast (PTC) and Class Token Contrast (CTC), in the Vision Transformer, the issue of over-smoothing produced by ViT is addressed, thereby improving the weakly supervised semantic segmentation performance using only image-level labels.

Token Turing Machines

Michael S. Ryoo (Google Research), Anurag Arnab (Google Research)

CodeRecognitionObject DetectionRobotic IntelligenceTransformerVideo

🎯 What it does: Proposes the Token Turing Machine (TTM), an autoregressive Transformer with external memory, designed for efficiently handling long-sequence visual understanding tasks;

TokenHPE: Learning Orientation Tokens for Efficient Head Pose Estimation via Transformers

Cheng Zhang (Central China Normal University), Youfu Li (City University of Hong Kong)

CodePose EstimationTransformerImage

🎯 What it does: A TokenHPE method based on Transformer is proposed, which achieves head pose estimation by learning the relationships of key facial parts, showing excellent performance especially in extreme poses and occlusion scenarios.

Toward Stable, Interpretable, and Lightweight Hyperspectral Super-Resolution

Wen-jin Guo (Xidian University), Leyuan Fang (Hunan University)

CodeRestorationSuper ResolutionOptimizationExplainability and InterpretabilityComputational EfficiencyAuto EncoderImage

🎯 What it does: A lightweight hyperspectral image super-resolution framework based on coordinated optimization is proposed, utilizing explicit degradation estimation and a sparse mixture prior autoencoder to recover high spatial resolution HSI.

Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation

Mayu Otani (CyberAgent), Shin’ichi Satoh

CodeGenerationData SynthesisDiffusion modelImageTextReview/Survey PaperBenchmark

🎯 What it does: This paper conducts a systematic investigation and summarizes the current state of human evaluation in the text-to-image generation field, finding a lack of standardization and poor reproducibility. Subsequently, a unified evaluation protocol based on absolute scoring is designed and validated, along with the public release of implementations, templates, and evaluation data.

Towards Artistic Image Aesthetics Assessment: A Large-Scale Dataset and a New Method

Ran Yi (Shanghai Jiao Tong University), Paul L. Rosin (Cardiff University)

CodeClassificationRecommendation SystemConvolutional Neural NetworkImage

🎯 What it does: This paper presents a large-scale aesthetic assessment dataset for artistic images, BAID (60,337 artworks, 360,000+ votes), and designs the Style-specific Art Assessment Network (SAAN) model for automatic evaluation of the aesthetic quality of artistic images.

Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks

Simin Li (Beihang University), Xianglong Liu

CodeAutonomous DrivingAdversarial AttackImageBenchmark

🎯 What it does: This study investigates the visual naturalness of physical world adversarial attacks and proposes an automatic evaluation method.

Towards Better Stability and Adaptability: Improve Online Self-Training for Model Adaptation in Semantic Segmentation

Dong Zhao (Xidian University), Licheng Jiao (Xidian University)

CodeSegmentationDomain AdaptationImage

🎯 What it does: This paper proposes a source-agnostic semantic segmentation model adaptation method called DT-ST, which implements online self-training through dynamic teacher updates and training consistency resampling.

Towards Bridging the Performance Gaps of Joint Energy-Based Models

Xiulong Yang (Georgia State University), Shihao Ji (Georgia State University)

CodeClassificationGenerationImageStochastic Differential Equation

🎯 What it does: An improved Joint Energy-based Model (JEM) called SADA-JEM is proposed, which utilizes a single network to simultaneously perform image classification and generation.

Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration

Kemal Oksuz (Five AI Ltd), Puneet K. Dokania (Five AI Ltd)

CodeObject DetectionDomain AdaptationImage

🎯 What it does: This paper proposes the Self-Aware Object Detection (SAOD) task, which requires detectors to have reliable uncertainty estimation, good calibration, and robustness to domain transfer in safety-critical scenarios.

Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition

Xiao Yang (Tsinghua University), Jun Zhu (Tsinghua University)

CodeRecognitionAdversarial AttackImageMultimodalityMesh

🎯 What it does: This study designs and implements an adversarial texture mesh (AT3D) that can be 3D printed in real environments for physical black-box attacks on facial recognition systems while circumventing multimodal anti-spoofing mechanisms.

Towards Effective Visual Representations for Partial-Label Learning

Shiyu Xia (Southeast University), Xin Geng (Southeast University)

CodeRepresentation LearningContrastive LearningImage

🎯 What it does: A partial label learning framework named PaPi is proposed, eliminating the contrastive learning module and using prototype alignment to guide the linear classifier's self-teaching, significantly improving representation learning and label disambiguation performance.

Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors

Gongjie Zhang (Nanyang Technological University), Shijian Lu (SenseTime Research)

CodeObject DetectionPose EstimationComputational EfficiencyTransformerImage

🎯 What it does: A framework named Iterative Multi-Scale Feature Aggregation (IMFA) is proposed to improve the efficiency and effectiveness of Transformer-based object detectors in utilizing multi-scale features.

Towards Modality-Agnostic Person Re-Identification With Descriptive Query

Cuiqun Chen (Wuhan University), Ding Jiang (Wuhan University)

CodeRecognitionRetrievalTransformerContrastive LearningTextMultimodality

🎯 What it does: This paper studies a modality-agnostic person re-identification framework called UNIReID, which can simultaneously handle text, sketches, and joint queries of both, addressing the issue of modality uncertainty.

Towards Practical Plug-and-Play Diffusion Models

Hyojun Go (Riiid AI Research), Seungtaek Choi (Riiid AI Research)

CodeSegmentationGenerationKnowledge DistillationMixture of ExpertsDiffusion modelImage

🎯 What it does: The PPAP framework is proposed, utilizing multiple experts, parameter-efficient fine-tuning, and unsupervised knowledge transfer, allowing publicly available offline models to achieve conditional guidance in diffusion models in a plug-and-play manner.

Towards Realistic Long-Tailed Semi-Supervised Learning: Consistency Is All You Need

Tong Wei (Southeast University), Kai Gan (Southeast University)

CodeClassificationConvolutional Neural NetworkContrastive LearningImage

🎯 What it does: An Adaptive Consistency Regularization (ACR) framework is proposed, utilizing a dual-branch network and dynamic logit adjustment to address the issue of unknown class distribution of unlabeled data in long-tail semi-supervised learning.

Towards Robust Tampered Text Detection in Document Image: New Dataset and New Solution

Chenfan Qu (South China University of Technology), Lianwen Jin (South China University of Technology)

CodeClassificationAnomaly DetectionConvolutional Neural NetworkTransformerImageText

🎯 What it does: A document image tampering text detection framework based on visual and frequency domain dual modalities is proposedβ€”Document Tampering Detector (DTD). It introduces a technical solution utilizing Frequency Perception Head (FPH), Multi-view Iterative Decoder (MID), and Adaptive Compression Curriculum Learning (CLTD) to enhance detection accuracy and robustness. Additionally, a new tampered text dataset, DocTamper, consisting of 170,000 images, has been constructed.

Towards Unbiased Volume Rendering of Neural Implicit Surfaces With Geometry Priors

Yongqiang Zhang (NetEase Fuxi AI Lab), Changjie Fan (NetEase Fuxi AI Lab)

CodeGenerationData SynthesisNeural Radiance FieldPoint Cloud

🎯 What it does: A method for converting unbiased perspective SDF to voxel rendering is proposed, combined with MVS point cloud supervision to achieve mask-free neural implicit surface reconstruction.

Towards Unified Scene Text Spotting Based on Sequence Generation

Taeho Kil (Naver Cloud), Daehee Kim (Naver Cloud)

CodeRecognitionObject DetectionTransformerMixture of ExpertsImageText

🎯 What it does: A unified scene text detection and recognition model UNITS based on sequence generation is proposed, capable of handling four detection formats: center points, bounding boxes, quadrilaterals, and polygons within a single model, and achieving ultra-long sequence inference through starting point prompts.

Towards Universal Fake Image Detectors That Generalize Across Generative Models

Utkarsh Ojha (University of Wisconsin Madison), Yong Jae Lee (University of Wisconsin Madison)

CodeClassificationData SynthesisAnomaly DetectionTransformerVision Language ModelGenerative Adversarial NetworkContrastive LearningImage

🎯 What it does: This paper studies the problem of detecting fake images generated by generative models and finds that traditional binary classifiers have poor generalization ability across models.

TRACE: 5D Temporal Regression of Avatars With Dynamic Cameras in 3D Environments

Yu Sun (Harbin Institute of Technology), Michael J. Black (Max Planck Institute for Intelligent Systems)

CodeObject TrackingPose EstimationConvolutional Neural NetworkRecurrent Neural NetworkOptical FlowVideo

🎯 What it does: We propose TRACE, a single-stage network based on 5D representation that can simultaneously regress the 3D poses, shapes, and global trajectories of multiple people under dynamic cameras.

Train/Test-Time Adaptation With Retrieval

Luca Zancato (AWS AI Labs), Stefano Soatto (AWS AI Labs)

CodeRetrievalDomain AdaptationContrastive LearningImage

🎯 What it does: A method called TAR3 is proposed, which can adaptively pre-train models by retrieving external unlabeled samples during both training and inference.

Trainable Projected Gradient Method for Robust Fine-Tuning

Junjiao Tian (Georgia Institute of Technology), Zsolt Kira (Georgia Institute of Technology)

CodeDomain AdaptationOptimizationTransformerSupervised Fine-TuningImage

🎯 What it does: A trainable projection gradient method (TPGM) is proposed, which automatically learns the distance constraints between each layer and the pre-trained model during the fine-tuning process, thereby improving OOD robustness while maintaining ID performance.

Transformer-Based Learned Optimization

Erik GΓ€rtner (Google Research), Cristian Sminchisescu (Google Research)

CodePose EstimationOptimizationTransformerTabularTime Series

🎯 What it does: This paper proposes a Transformer-based learning optimizer called Optimus, which utilizes neural networks to learn each step's updates and precondition matrices, achieving more efficient iterative optimization.

Transforming Radiance Field With Lipschitz Network for Photorealistic 3D Scene Stylization

Zicheng Zhang (University of Chinese Academy of Sciences), Ting Yao (HiDream.ai Inc.)

CodeGenerationData SynthesisNeural Radiance FieldImage

🎯 What it does: Constructed the LipRF framework, utilizing the appearance representation of the pre-trained NeRF and the mapping of Lipschitz MLP to achieve cross-view consistency and lighting realism in 3D scene stylization.

TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning With Structure-Trajectory Prompted Reconstruction for Person Re-Identification

Haocong Rao (Nanyang Technological University), Chunyan Miao (Nanyang Technological University)

CodeRecognitionRetrievalGraph Neural NetworkTransformerContrastive LearningGraph

🎯 What it does: This paper proposes the TranSG framework for person re-identification (re-ID) based on 3D skeleton graphs.

Trap Attention: Monocular Depth Estimation With Manual Traps

Chao Ning (Northwestern Polytechnical University), Hongping Gan (Northwestern Polytechnical University)

CodeDepth EstimationTransformerImage

🎯 What it does: This paper proposes a new Trap Attention mechanism that combines depthwise separable convolutions and manually defined trap functions, enabling global feature interaction while maintaining linear complexity, thus achieving monocular depth estimation.

Tree Instance Segmentation With Temporal Contour Graph

Adnan Firoze (Purdue University), Daniel Aliaga (Purdue University)

CodeObject DetectionSegmentationGraph Neural NetworkOptical FlowImageVideo

🎯 What it does: This paper proposes a method for crown instance segmentation and counting based on RGB sequences collected by UAVs. It first performs over-segmentation on the sequences and constructs contour maps, then uses Graph Convolutional Networks (GCN) to learn contour features and complete crown merging, resulting in accurate instance masks and tree counts.

Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction

Yuanhui Huang (Tsinghua University), Jiwen Lu (Tsinghua University)

CodeSegmentationAutonomous DrivingTransformerImagePoint Cloud

🎯 What it does: This paper proposes a Three-View (TPV) representation and the TPVFormer transformer model, which predicts 3D semantic occupancy volumes using only camera input combined with sparse LiDAR annotations, achieving complete spatial semantic occupancy prediction.

TriDet: Temporal Action Detection With Relative Boundary Modeling

Dingfeng Shi (Beihang University), Dacheng Tao (JD Explore Academy)

CodeRecognitionObject DetectionConvolutional Neural NetworkVideo

🎯 What it does: This paper proposes a one-stage temporal action detection framework called TriDet, which combines the Trident-head and SGP layer to model the relative probability distribution of action boundaries and achieve scalable granularity perception in the feature pyramid.

TriVol: Point Cloud Rendering via Triple Volumes

Tao Hu (Chinese University of Hong Kong), Jiaya Jia (Chinese University of Hong Kong)

CodeGenerationData SynthesisNeural Radiance FieldPoint Cloud

🎯 What it does: This paper proposes TriVol, a three-volume method for generating high-quality, hole-free rendered images from sparse point clouds.

TrojDiff: Trojan Attacks on Diffusion Models With Diverse Targets

Weixin Chen (University of Illinois Urbana-Champaign), Bo Li (University of Illinois Urbana-Champaign)

CodeGenerationAdversarial AttackDiffusion modelImage

🎯 What it does: The paper proposes a Trojan attack method for diffusion models called TrojDiff, which can inject triggers during training, allowing the model to generate preset attack targets when receiving trigger noise.

Tunable Convolutions With Parametric Multi-Loss Optimization

Matteo Maggioni (Huawei), AleΕ‘ Leonardis (Huawei)

CodeImage TranslationOptimizationConvolutional Neural NetworkImage

🎯 What it does: A tunable convolution layer is proposed that can adjust the behavior of neural networks through interactive parameters during inference, combined with a parameterized multi-objective loss to achieve multi-objective control.

Turning a CLIP Model Into a Scene Text Detector

Wenwen Yu (Huazhong University of Science and Technology), Xiang Bai (Huazhong University of Science and Technology)

CodeObject DetectionDomain AdaptationTransformerPrompt EngineeringContrastive LearningImageText

🎯 What it does: Directly transform the pre-trained CLIP model into a scene text detector (TCM) without additional pre-training steps.

Turning Strengths Into Weaknesses: A Certified Robustness Inspired Attack Framework Against Graph Neural Networks

Binghui Wang (Illinois Institute of Technology), Yun Dong (Nanchang University)

CodeAdversarial AttackGraph Neural NetworkGraph

🎯 What it does: A robust attack framework based on authentication has been designed, utilizing the authentication perturbation size of nodes to guide graph structure attacks, thereby enhancing the effectiveness of existing attack methods.

Twin Contrastive Learning With Noisy Labels

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

CodeClassificationRepresentation LearningContrastive LearningImage

🎯 What it does: Proposes the Twin Contrastive Learning (TCL) model, which combines contrastive learning with Gaussian Mixture Models (GMM) to learn robust representations from data with noisy labels and automatically correct the labels.

Two-Shot Video Object Segmentation

Kun Yan (Peking University), Yan Lu (Microsoft Research Asia)

CodeObject DetectionSegmentationVideo

🎯 What it does: This paper proposes a two-frame video object segmentation (Two-Shot VOS) training framework that uses annotations from only two frames of each video, leveraging pseudo-labels and semi-supervised learning to enhance model performance.

ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding

Le Xue (Salesforce Research), Silvio Savarese (Stanford University)

CodeClassificationRecognitionRepresentation LearningContrastive LearningMultimodalityPoint Cloud

🎯 What it does: This paper proposes the ULIP framework, which aligns 3D point cloud features using the pre-trained CLIP image-text feature space to construct a unified representation of language, images, and point clouds in three modalities.

Ultra-High Resolution Segmentation With Ultra-Rich Context: A Novel Benchmark

Deyi Ji (University of Science and Technology of China), Jieping Ye (Alibaba Group)

CodeSegmentationConvolutional Neural NetworkImageBenchmark

🎯 What it does: A new benchmark dataset for UHR semantic segmentation, URUR, and an improved segmentation model, WSDNet, are proposed.

Ultrahigh Resolution Image/Video Matting With Spatio-Temporal Sparsity

Yanan Sun (Hong Kong University of Science and Technology), Yu-Wing Tai (Hong Kong University of Science and Technology)

CodeSegmentationComputational EfficiencyConvolutional Neural NetworkSupervised Fine-TuningImageVideo

🎯 What it does: This paper presents SparseMat, an efficient framework for high-resolution image/video matting;

Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection

Hui Lv (Nanjing University of Science and Technology), Hanwang Zhang (Nanyang Technological University)

CodeAnomaly DetectionVideo

🎯 What it does: Proposed Unbiased Multiple Instance Learning (UMIL) for weakly supervised video anomaly detection.

Unbiased Scene Graph Generation in Videos

Sayak Nag (University of California), Amit K. Roy-Chowdhury (University of California)

CodeObject DetectionGenerationTransformerContrastive LearningVideo

🎯 What it does: The TEMPURA framework is proposed for unbiased dynamic scene graph generation, addressing issues such as long-tail distribution, noise, and temporal inconsistency.

Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection

Fan Lu (University of Science and Technology of China), Yang Cao (University of Science and Technology of China)

CodeAnomaly DetectionOptimizationConvolutional Neural NetworkContrastive LearningImage

🎯 What it does: This paper addresses the Semantically Coherent Out-of-Distribution (SCOOD) detection task and proposes an energy-based uncertainty-aware optimal transport (ET) scheme. By assigning semantically consistent labels to unlabeled data and combining a cross-set expansion strategy (Lrep) to enhance semantic discrimination, it achieves more accurate OOD detection.

Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models

Qiucheng Wu (University of California), Shiyu Chang (University of California)

CodeGenerationData SynthesisDiffusion modelImageText

🎯 What it does: This study investigates the intrinsic attribute decoupling capability of Stable Diffusion and proposes that optimizing only the mixed weights of two text embeddings can achieve various image editing tasks without fine-tuning the model.

Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction

Yi Xu (Northeastern University), Yun Fu (Northeastern University)

CodeRecurrent Neural NetworkGraph Neural NetworkTime SeriesSequential

🎯 What it does: A unified GC-VRNN framework is proposed, capable of simultaneously performing missing value imputation for multi-agent trajectories and future trajectory prediction.

Uncurated Image-Text Datasets: Shedding Light on Demographic Bias

Noa Garcia (Osaka University), Yuta Nakashima (Osaka University)

CodeObject DetectionGenerationRetrievalTransformerVision Language ModelDiffusion modelImageTextMultimodality

🎯 What it does: This study constructs PHASE annotations containing six perceptual attributes: age, gender, skin color, race, emotion, and activity on the large-scale unfiltered image-text dataset GCC, and evaluates the social biases and amplification phenomena in image description, CLIP embedding, and text-to-image generation tasks based on this.

Understanding and Improving Features Learned in Deep Functional Maps

Souhaib Attaiki (Γ‰cole Polytechnique), Maks Ovsjanikov (Γ‰cole Polytechnique)

CodeOptimizationRepresentation LearningGraph Neural NetworkContrastive LearningPoint CloudMesh

🎯 What it does: This paper studies the geometric meaning of the feature functions learned in deep functional maps and proposes two simple improvement methods to enhance the accuracy of shape correspondence.

Understanding and Improving Visual Prompting: A Label-Mapping Perspective

Aochuan Chen (Michigan State University), Sijia Liu (MIT-IBM Watson AI Lab)

CodeClassificationOptimizationExplainability and InterpretabilityPrompt EngineeringContrastive LearningImage

🎯 What it does: A visual prompting framework based on label mapping (LM) called ILM-VP is proposed, which can improve the accuracy of the target task and enhance interpretability through co-learning of LM and visual prompts via iterative optimization, without fine-tuning the source model.

Understanding Imbalanced Semantic Segmentation Through Neural Collapse

Zhisheng Zhong (Chinese University of Hong Kong), Jiaya Jia (Chinese University of Hong Kong)

CodeSegmentationConvolutional Neural NetworkSupervised Fine-TuningImagePoint Cloud

🎯 What it does: This paper studies the geometric structure of the last layer feature centers and classifiers in semantic segmentation. It finds that, unlike the neural collapse in image classification, semantic segmentation loses isometric symmetry in feature centers and classifiers due to contextual relevance and class imbalance, leading to poor performance in minority classes.

Unicode Analogies: An Anti-Objectivist Visual Reasoning Challenge

Steven Spratley (University of Melbourne), Tim Miller (University of Melbourne)

CodeConvolutional Neural NetworkImage

🎯 What it does: Designed and released an advanced matrix problem (Unicode Analogies) dataset based on Unicode characters to evaluate the analogy reasoning and fluid conceptualization capabilities of visual systems;

Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation

Liulei Li (Zhejiang University), Yi Yang (ETH Zurich)

CodeObject DetectionSegmentationConvolutional Neural NetworkContrastive LearningVideo

🎯 What it does: This paper proposes a completely label-free video object segmentation method that automatically generates pseudo-masks through spatiotemporal pixel clustering on unlabeled videos, and jointly learns mask embeddings and cross-frame correspondences. The trained network can directly perform mask-based continuous segmentation.

Unifying Vision, Text, and Layout for Universal Document Processing

Zineng Tang (University of North Carolina at Chapel Hill), Mohit Bansal (University of North Carolina at Chapel Hill)

CodeClassificationRecognitionGenerationTransformerImageTextMultimodalityBenchmark

🎯 What it does: This paper presents UDOP, a unified document AI foundation model capable of simultaneously processing visual, textual, and layout information, and consolidating various document tasks into a sequence generation framework, supporting document understanding, question answering, information extraction, classification, as well as document generation and editing.

UniHCP: A Unified Model for Human-Centric Perceptions

Yuanzheng Ci (University of Sydney), Wanli Ouyang (Shanghai AI Laboratory)

CodeRecognitionObject DetectionSegmentationPose EstimationTransformerImage

🎯 What it does: This paper presents UniHCP, a unified Vision Transformer model capable of simultaneously handling five types of human perception tasks: pose estimation, human segmentation, pedestrian detection, person re-identification (ReID), and attribute recognition.

Universal Instance Perception As Object Discovery and Retrieval

Bin Yan (Dalian University of Technology), Huchuan Lu (Dalian University of Technology)

CodeObject DetectionObject TrackingSegmentationRetrievalTransformerPrompt EngineeringImageVideoText

🎯 What it does: A unified instance-aware model called UNINEXT is proposed, which can complete 10 types of instance-aware sub-tasks, including object detection, instance segmentation, video tracking, and semantic video segmentation, within the same framework through prompts (category names, language expressions, reference boxes/masks).

Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objects

Wenteng Liang (Beijing University of Posts and Telecommunications), Anlong Ming (Chongqing University of Posts and Telecommunications)

CodeObject DetectionConvolutional Neural NetworkImageBenchmark

🎯 What it does: The UnSniffer framework is proposed to simultaneously detect unknown objects and known objects under known categories in object detection.

Unpaired Image-to-Image Translation With Shortest Path Regularization

Shaoan Xie (Carnegie Mellon University), Kun Zhang (Carnegie Mellon University)

CodeImage TranslationGenerationAuto EncoderGenerative Adversarial NetworkImage

🎯 What it does: A framework for unpaired image translation based on the shortest path assumption is proposed, constructing a continuous path from the source domain to the target domain, and constraining the generative model by regularizing the path length.

Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration

Guofeng Mei (University of Technology Sydney), Qiang Wu

CodeRecognitionOptimizationTransformerGaussian SplattingPoint Cloud

🎯 What it does: An unsupervised deep probabilistic point cloud registration framework, UDPReg, is proposed, capable of handling partially overlapping point clouds.

Unsupervised Inference of Signed Distance Functions From Single Sparse Point Clouds Without Learning Priors

Chao Chen (Tsinghua University), Zhizhong Han (Wayne State University)

CodeGenerationData SynthesisOptimizationPoint Cloud

🎯 What it does: An end-to-end network is proposed that does not require signed distance supervision, priors, or normal information, capable of directly inferring the Signed Distance Function (SDF) from a single sparse point cloud.

Unsupervised Intrinsic Image Decomposition With LiDAR Intensity

Shogo Sato (NTT Human Informatics Laboratories), Jun Shimamura (NTT Communication Science Laboratories)

CodeRestorationGenerationAuto EncoderGenerative Adversarial NetworkImagePoint Cloud

🎯 What it does: This paper proposes an unsupervised intrinsic image decomposition method using LiDAR intensity (IID-LI), which decomposes color images into albedo and shade components.

Unsupervised Object Localization: Observing the Background To Discover Objects

Oriane SimΓ©oni (Valeo.ai), Patrick PΓ©rez (Valeo.ai)

CodeObject DetectionSegmentationTransformerContrastive LearningImage

🎯 What it does: By first identifying the image background and utilizing background seeds extracted through self-supervised Transformer attention, high-quality foreground masks are obtained through self-supervised training with a minimal 1Γ—1 convolutional layer on frozen DINO features, thus achieving unsupervised object localization.

Unsupervised Space-Time Network for Temporally-Consistent Segmentation of Multiple Motions

Etienne Meunier (Inria), Patrick Bouthemy (Inria)

CodeObject TrackingSegmentationConvolutional Neural NetworkOptical FlowVideo

🎯 What it does: This paper proposes an unsupervised 3D U-Net network that utilizes a volume of optical flow over time for multi-motion segmentation, and is trained using a spatiotemporal parameter motion model and temporal consistency regularization.

Unsupervised Visible-Infrared Person Re-Identification via Progressive Graph Matching and Alternate Learning

Zesen Wu (Wuhan University), Mang Ye (Wuhan University)

CodeRecognitionRetrievalGraph Neural NetworkContrastive LearningImageMultimodality

🎯 What it does: A framework for unsupervised visible-infrared person re-identification is proposed, which utilizes progressive graph matching to mine cross-modal correspondences and reduces modal discrepancies through alternating cross-modal contrastive learning.

Upcycling Models Under Domain and Category Shift

Sanqing Qu (Tongji University), Changjun Jiang (Tongji University)

CodeDomain AdaptationImage

🎯 What it does: This paper proposes a source unsupervised general domain adaptation method based on global and local clustering (GLC), which can achieve model reuse for domain shift and category shift under the premise of using only a closed-set model pre-trained on the source domain.

V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting

Haibao Yu (Tsinghua University), Zaiqing Nie (Baidu Inc.)

CodeObject TrackingAutonomous DrivingTransformerSimultaneous Localization and MappingTime SeriesSequential

🎯 What it does: This paper presents the V2X-Seq large-scale continuous V2X dataset, which includes synchronized perception and trajectory prediction data for vehicles and infrastructure.

Variational Distribution Learning for Unsupervised Text-to-Image Generation

Minsoo Kang (Seoul National University), Bohyung Han (Seoul National University)

CodeGenerationData SynthesisKnowledge DistillationDiffusion modelGenerative Adversarial NetworkContrastive LearningImageTextMultimodality

🎯 What it does: In the absence of image-text paired annotations, this paper proposes to use the CLIP pre-trained model to estimate the text embeddings corresponding to images and to train a text-to-image generation model by maximizing the likelihood in an unsupervised manner through variational inference.

VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization

Bingfan Zhu (Zhejiang University), Leonidas Guibas (Stanford University)

CodeDepth EstimationKnowledge DistillationNeural Radiance FieldPoint Cloud

🎯 What it does: A perspective-dependent normalization-based NeRF training framework (VDN-NeRF) is proposed, which extracts viewpoint-invariant deep features through self-distillation to suppress shape-radiance ambiguity and improve the quality of geometric reconstruction under non-Lambertian surfaces and dynamic lighting conditions.

VectorFloorSeg: Two-Stream Graph Attention Network for Vectorized Roughcast Floorplan Segmentation

Bingchen Yang (University of Chinese Academy of Sciences), Jun Xiao (University of Chinese Academy of Sciences)

CodeSegmentationGraph Neural NetworkImageGraph

🎯 What it does: This paper addresses the semantic segmentation of rooms in roughly drawn vector floor plans (house floor plans), specifically predicting the spatial area and category of each room.

Video Dehazing via a Multi-Range Temporal Alignment Network With Physical Prior

Jiaqi Xu (Chinese University of Hong Kong), Pheng-Ann Heng (Chinese University of Hong Kong)

CodeRestorationTransformerOptical FlowVideo

🎯 What it does: This paper proposes a MAP-Net based on multi-range spatiotemporal alignment for restoring fog-free frames in videos.

Video Test-Time Adaptation for Action Recognition

Wei Lin (Graz University of Technology), Horst Bischof (Graz University of Technology)

CodeDomain AdaptationVideo

🎯 What it does: This paper proposes an online video test-time adaptation method called ViTTA, aimed at improving action recognition performance on test videos with distribution shifts.

Viewpoint Equivariance for Multi-View 3D Object Detection

Dian Chen (Toyota Research Institute), Adrien Gaidon (Toyota Research Institute)

CodeObject DetectionAutonomous DrivingTransformerPoint Cloud

🎯 What it does: A Transformer-based multi-view 3D object detection framework VEDet is proposed, which utilizes viewpoint equivariance to learn the consistency of objects across different camera perspectives, thereby improving 3D localization accuracy.

VindLU: A Recipe for Effective Video-and-Language Pretraining

Feng Cheng (University of North Carolina), Gedas Bertasius (University of North Carolina)

CodeRetrievalTransformerVision Language ModelVideoTextMultimodality

🎯 What it does: Systematically study and propose a step-by-step recipe for transitioning from image to video-language pre-training, called VINDLU;

Virtual Sparse Convolution for Multimodal 3D Object Detection

Hai Wu (Xiamen University), Cheng Wang (Texas A&M University)

CodeObject DetectionAutonomous DrivingConvolutional Neural NetworkMultimodalityPoint Cloud

🎯 What it does: A novel sparse convolution (VirConv) is proposed to integrate virtual points obtained through depth completion and LiDAR points, achieving efficient multi-modal 3D object detection.

VisFusion: Visibility-Aware Online 3D Scene Reconstruction From Videos

Huiyu Gao (Australian National University), Miaomiao Liu (Australian National University)

CodeConvolutional Neural NetworkRecurrent Neural NetworkSimultaneous Localization and MappingVideo

🎯 What it does: This paper proposes an online, visually perceptive 3D scene reconstruction method called VisFusion, which can generate detailed and dense 3D models in real-time from calibrated monocular video.

Visibility Constrained Wide-Band Illumination Spectrum Design for Seeing-in-the-Dark

Muyao Niu (University of Tokyo), Yinqiang Zheng (University of Tokyo)

CodeRestorationOptimizationConvolutional Neural NetworkImage

🎯 What it does: This paper proposes a visual constraint broadband spectral design method to optimize the mixed lighting of visible and near-infrared LEDs, aiming to enhance RGB reconstruction effects in completely dark environments.

Vision Transformers Are Good Mask Auto-Labelers

Shiyi Lan (NVIDIA), Anima Anandkumar (NVIDIA)

CodeObject DetectionSegmentationTransformerImage

🎯 What it does: A two-stage framework and Mask Auto-Labeler are proposed to automatically generate high-quality masks under box supervision for instance segmentation training.

Visual Dependency Transformers: Dependency Tree Emerges From Reversed Attention

Mingyu Ding (University of Hong Kong), Chuang Gan (MIT)

CodeClassificationObject DetectionSegmentationTransformerImageVideo

🎯 What it does: This paper proposes a visually dependent Transformer (DependencyViT) that achieves unsupervised construction of a hierarchical dependency tree of image patches through reverse attention, and designs a lightweight version (DependencyViT-Lite) to implement dynamic visual pooling.

Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Images

Ming Y. Lu (Massachusetts Institute of Technology), Faisal Mahmood (Harvard University)

CodeClassificationTransformerPrompt EngineeringContrastive LearningImageTextBiomedical Data

🎯 What it does: Proposes the MI-Zero framework, which utilizes contrastive vision-language pre-trained models to achieve zero-shot transfer for large-sized whole slide images (WSI) through multi-instance learning, completing cancer subtype classification.