arXivSub Start free trial

ICCV 2023 Papers with Code β€” Page 3

IEEE/CVF International Conference on Computer Vision Β· 743 papers

EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation

Suman Saha (ETH Zurich), Luc Van Gool (ETH Zurich)

CodeSegmentationDomain AdaptationTransformerImage

🎯 What it does: A framework called EDAPS specifically designed for domain adaptive panoptic segmentation is proposed, achieving end-to-end training on a dataset transitioning from synthetic to real scenes.

Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory

Ting Lei (Wangxuan Institute of Computer Technology Peking University), Yang Liu (Wangxuan Institute of Computer Technology Peking University)

CodeRecognitionObject DetectionTransformerContrastive LearningImage

🎯 What it does: A training-free and lightweight fine-tuning framework for person-object interaction detection, ADA-CM, is proposed, utilizing a concept-guided memory module and instance-aware adapter for efficient detection.

Efficient Computation Sharing for Multi-Task Visual Scene Understanding

Sara Shoouri (University of Michigan), Hun-Seok Kim (University of Michigan)

CodeSegmentationDepth EstimationComputational EfficiencyTransformerDiffusion modelImageVideo

🎯 What it does: This paper proposes a Transformer-based multi-task visual scene understanding framework that utilizes the weights and activations of single-task models for cross-task and cross-time sharing to achieve efficient multi-task inference.

Efficient Diffusion Training via Min-SNR Weighting Strategy

Tiankai Hang (Southeast University), Baining Guo (Microsoft Research Asia)

CodeGenerationData SynthesisOptimizationComputational EfficiencyTransformerDiffusion modelAuto EncoderImage

🎯 What it does: A loss weighting strategy named Min‑SNRΞ³ is proposed to adjust the gradient conflicts at different time steps during the training of diffusion models, thereby accelerating convergence and improving generation quality.

Efficient LiDAR Point Cloud Oversegmentation Network

Le Hui (Northwestern Polytechnical University), Jian Yang (Nanjing University of Science and Technology)

CodeSegmentationAutonomous DrivingConvolutional Neural NetworkPoint Cloud

🎯 What it does: The SuperLiDAR network is proposed for end-to-end over-segmentation of LiDAR point clouds, generating superpoints that are uniform in both semantics and geometry.

Efficient Video Action Detection with Token Dropout and Context Refinement

Lei Chen (Nanjing University), Limin Wang (Nanjing University)

CodeRecognitionObject DetectionComputational EfficiencyTransformerVideo

🎯 What it does: This paper proposes an efficient video action detection framework EVAD based on ViT, achieving efficient inference through spatiotemporal token dropping centered on key frames and context refinement.

EfficientViT: Lightweight Multi-Scale Attention for High-Resolution Dense Prediction

Han Cai (Massachusetts Institute of Technology), Song Han (Massachusetts Institute of Technology)

CodeClassificationSegmentationSuper ResolutionTransformerSupervised Fine-TuningImage

🎯 What it does: This paper proposes the EfficientViT model, which achieves high-resolution dense prediction through lightweight multi-scale attention.

EGC: Image Generation and Classification via a Diffusion Energy-Based Model

Qiushan Guo (University of Hong Kong), Ping Luo (University of Hong Kong)

CodeClassificationGenerationDiffusion modelImage

🎯 What it does: A unified energy-based model EGC is proposed, which can perform image classification and generate images through a diffusion reverse process. The forward process estimates the energy of the joint distribution p(x, y), while the backward process computes the gradient of the joint distribution for sample reconstruction and generation.

EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries

Jinjie Mai (King Abdullah University of Science and Technology), Bernard Ghanem (King Abdullah University of Science and Technology)

CodeObject DetectionPose EstimationRetrievalSimultaneous Localization and MappingVideo

🎯 What it does: An end-to-end visual query 3D localization (VQ3D) pipeline called EgoLoc is proposed to locate the most recent appearance of the queried object in first-person videos and provide a relative 3D displacement vector.

EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding

Chenchen Zhu (Meta AI), Zhicheng Yan (Meta AI)

CodeObject DetectionFederated LearningVideo

🎯 What it does: Created a large-scale first-person perspective EgoObjects dataset, containing hundreds of thousands of video frames and target boxes, annotated with category and instance IDs;

EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone

Shraman Pramanick (Johns Hopkins University), Pengchuan Zhang (Meta AI)

CodeRetrievalRepresentation LearningTransformerContrastive LearningVideoTextMultimodality

🎯 What it does: We propose EgoVLPv2, a second-generation self-centered video-language pre-training framework that integrates cross-modal attention into the video and text Transformer backbone.

EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition

Gabriele Berton (Politecnico di Torino), Carlo Masone (Politecnico di Torino)

CodeRecognitionRetrievalConvolutional Neural NetworkContrastive LearningImage

🎯 What it does: In the visual place recognition task, a training method is proposed that does not require additional annotations, utilizing map partitioning and principal component analysis to automatically construct multi-view classes of the same location, thereby training a global descriptor that is robust to viewpoint changes.

ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices

Chen Tang (Tsinghua University), Mao Yang (Microsoft Research)

CodeClassificationObject DetectionOptimizationNeural Architecture SearchTransformerImage

🎯 What it does: This study proposes ElasticViT, a two-stage neural architecture search method designed for deploying high-accuracy, low-latency visual Transformer (ViT) models on various mobile devices.

ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation

Yuxiang Wei (Harbin Institute of Technology), Wangmeng Zuo (Harbin Institute of Technology)

CodeGenerationData SynthesisTransformerDiffusion modelContrastive LearningImageText

🎯 What it does: This paper proposes a learning-based encoder called ELITE, which quickly and accurately maps visual concepts to text embedding space, enabling customized text-to-image generation.

Empowering Low-Light Image Enhancer through Customized Learnable Priors

Naishan Zheng (University of Science and Technology of China), Feng Zhao (University of Science and Technology of China)

CodeRestorationConvolutional Neural NetworkAuto EncoderImage

🎯 What it does: This paper proposes a customizable and learnable prior deep unrolling framework (CUE) for low-light image enhancement, utilizing Masked Autoencoder pre-trained illumination and noise priors, which are embedded in the proximal operations and regularization terms of the Retinex unrolling steps, thereby achieving a more transparent and interpretable enhancement model.

End-to-End Diffusion Latent Optimization Improves Classifier Guidance

Bram Wallace (Salesforce AI), Nikhil Naik (Salesforce AI)

CodeGenerationOptimizationDiffusion modelImageMultimodality

🎯 What it does: By directly performing gradient optimization on the noise vector of the diffusion model (DOODL), precise guidance is applied to the final generated images using pre-trained discriminative networks (such as CLIP, FGVC classifiers, and aesthetic scorers), achieving multimodal, personalized, and aesthetic optimization without the need to retrain noise-aware classifiers.

Enhanced Soft Label for Semi-Supervised Semantic Segmentation

Jie Ma (Sun Yat-sen University), Guanbin Li (Sun Yat-sen University)

CodeSegmentationConvolutional Neural NetworkContrastive LearningImage

🎯 What it does: This paper proposes a semi-supervised semantic segmentation framework based on enhanced soft labels (ESL), which combines dynamic soft labels (DSL) with pixel-to-part contrastive learning to fully utilize high-entropy pseudo-label information and improve category boundary recognition capabilities.

Enhancing Adversarial Robustness in Low-Label Regime via Adaptively Weighted Regularization and Knowledge Distillation

Dongyoon Yang (Seoul National University), Yongdai Kim (Seoul National University)

CodeKnowledge DistillationAdversarial AttackImage

🎯 What it does: In the scenario of limited labeled data, a semi-supervised adversarial training method is proposed that combines adaptive weighted regularization with semi-supervised knowledge distillation;

Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization

Mingli Zhu (Chinese University of Hong Kong), Baoyuan Wu (Chinese University of Hong Kong)

CodeClassificationOptimizationConvolutional Neural NetworkSupervised Fine-TuningImage

🎯 What it does: A fine-tuning strategy based on Sharpness-Aware Minimization (SAM) called FT-SAM is proposed to more effectively eliminate implanted backdoors when only a small number of clean samples are available.

Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts

Wenyan Cong (University of Texas at Austin), Zhangyang Wang (University of Texas at Austin)

CodeGenerationData SynthesisTransformerMixture of ExpertsNeural Radiance FieldImage

🎯 What it does: A general NeRF model GNT-MOVE has been constructed that can directly synthesize new views in unseen scenes.

Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning

Guan Gui (Nanjing University), Yinghuan Shi (Nanjing University)

CodeClassificationData-Centric LearningContrastive LearningImage

🎯 What it does: A Sample Adaptive Augmentation (SAA) framework is proposed to identify and apply more diverse augmentations to 'naive' samples in semi-supervised learning;

Environment Agnostic Representation for Visual Reinforcement Learning

Hyesong Choi (Ewha Womans University), Dongbo Min (Ewha Womans University)

CodeRobotic IntelligenceReinforcement LearningImageVideo

🎯 What it does: An Environment-Agnostic Reinforcement Learning (EAR) framework is proposed, which utilizes feature decomposition, reconstruction, and action-based state shift self-supervised objectives to extract environment-agnostic features for visual RL policy learning.

Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generation

Yukuan Min (Xidian University), Cheng Deng (Xidian University)

CodeObject DetectionGenerationGraph Neural NetworkSupervised Fine-TuningImageGraph

🎯 What it does: A framework named EICR is proposed, providing a unified solution to the issues of predicate category imbalance and subject-object pair context imbalance in scene graph generation.

eP-ALM: Efficient Perceptual Augmentation of Language Models

Mustafa Shukor (Sorbonne University), Matthieu Cord (Valeo)

CodeOptimizationComputational EfficiencyTransformerLarge Language ModelPrompt EngineeringVision Language ModelVideoTextMultimodalityAudio

🎯 What it does: We propose eP-ALM, a multimodal adaptation method that efficiently integrates large language models with visual/video/audio encoders using only a few linear projection layers and soft prompts, while nearly freezing all parameters.

EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localization

Minjung Kim (Seoul National University), Gunhee Kim (Seoul National University)

CodePose EstimationRetrievalTransformerSimultaneous Localization and MappingImagePoint Cloud

🎯 What it does: This paper proposes an end-to-end 3D point to 2D pixel localization method EP2P-Loc for large-scale visual localization;

EQ-Net: Elastic Quantization Neural Networks

Ke Xu (Anhui University), Xingyi Zhang (Anhui University)

CodeCompressionOptimizationKnowledge DistillationHyperparameter SearchConvolutional Neural NetworkImage

🎯 What it does: A flexible quantization neural network (EQ-Net) is proposed, which can generate quantized sub-networks of different bit widths, symmetric/asymmetric, and adjustable granularity through a single training session.

Equivariant Similarity for Vision-Language Foundation Models

Tan Wang (Nanyang Technological University), Lijuan Wang (Microsoft)

CodeRetrievalTransformerVision Language ModelContrastive LearningImageVideoTextMultimodalityBenchmark

🎯 What it does: This paper proposes and implements Equivariant Similarity Learning (EQSIM) in Vision-Language Models (VLM) and constructs a benchmark focused on visual minor changes (EQBEN), aiming to enhance the model's robustness under fine-grained semantic variations.

Erasing Concepts from Diffusion Models

Rohit Gandikota (Northeastern University), David Bau (Northeastern University)

CodeGenerationData SynthesisDiffusion modelScore-based ModelImageText

🎯 What it does: A method is proposed for text-to-image diffusion models that allows for the erasure of specified visual concepts using only concept names without any additional data on pre-trained model weights.

Essential Matrix Estimation using Convex Relaxations in Orthogonal Space

Arman Karimian (Boston University), Roberto Tron (Boston University)

CodePose EstimationOptimizationSimultaneous Localization and MappingImage

🎯 What it does: This paper proposes a new two-view structure from motion (SfM) method that uses a four-dimensional rotation matrix embedding to estimate the essential matrix, achieving a globally optimal solution through semidefinite relaxation and Riemannian gradient descent.

Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training

Xiao-Ming Wu (Sun Yat-sen University), Wei-Shi Zheng (Sun Yat-sen University)

CodeOptimizationConvolutional Neural NetworkImage

🎯 What it does: A new binary network training method called ReSTE is proposed, which improves STE to balance estimation error and gradient stability, achieving efficient binary training.

Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks

Qihan Huang (Zhejiang University), Mingli Song (Zhejiang University)

CodeExplainability and InterpretabilityConvolutional Neural NetworkImage

🎯 What it does: Proposed quantifiable metrics for evaluating the interpretability of part prototype networks, and based on this, improved ProtoPNet to enhance its prototype consistency and robustness.

Explicit Motion Disentangling for Efficient Optical Flow Estimation

Changxing Deng (University of Macau), Shuaicheng Liu (Megvii Technology)

CodeComputational EfficiencyTransformerOptical FlowImageVideo

🎯 What it does: An Explicit Motion Disentangling (EMD-Flow) framework is proposed, which explicitly separates global motion learning from local refinement, and achieves efficient optical flow estimation through two lightweight modules: Multi-scale Motion Aggregation (MMA) and Confidence-induced Flow Propagation (CFP).

Exploiting Proximity-Aware Tasks for Embodied Social Navigation

Enrico Cancelli (University of Padova), Lamberto Ballan (University of Padova)

CodeRobotic IntelligenceRecurrent Neural NetworkReinforcement LearningPoint Cloud

🎯 What it does: This paper proposes an end-to-end social navigation architecture that injects common-sense cognition of human-machine interaction into reinforcement learning strategies through two types of 'proximity perception tasks'β€”Risk Estimation and Proximity Compassβ€”achieving safe and efficient robot navigation in human environments.

Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Tracking

Ben Kang (Dalian University of Technology), Huchuan Lu (Dalian University of Technology)

CodeObject TrackingTransformerVideo

🎯 What it does: A lightweight hierarchical Vision Transformer tracking framework HiT is proposed, which utilizes a Bridge Module to fuse deep semantic features with shallow detail features, and enhances the relationship between the search and template through dual-image position encoding, constructing an efficient real-time visual tracker.

Exploring Model Transferability through the Lens of Potential Energy

Xiaotong Li (Peking University), Ling-Yu Duan (Peking University)

CodeClassificationDomain AdaptationRepresentation LearningContrastive LearningImagePhysics Related

🎯 What it does: A physics-driven method based on potential energy descent is proposed to simulate the representation dynamics in the process of transfer learning, thereby improving the transferability assessment of pre-trained models.

Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection

Shihao Wang (Beijing Institute of Technology), Xiangyu Zhang (MEGVII Technology)

CodeObject DetectionAutonomous DrivingTransformerVideoPoint Cloud

🎯 What it does: The StreamPETR framework is proposed, achieving online long-sequence 3D detection based on object queries.

Exploring Predicate Visual Context in Detecting of Human-Object Interactions

Frederic Z Zhang, Stephen Gould (Australian National University)

CodeClassificationObject DetectionTransformerImage

🎯 What it does: This paper proposes an improved two-stage Transformer structure for detecting human-object interactions (HOI), enhancing predicate classification by incorporating box-pair-based positional information and richer image context into the cross-attention mechanism.

Exploring the Benefits of Visual Prompting in Differential Privacy

Yizhe Li (Xi'an Jiaotong University), Xuebin Ren (IBM Research)

CodeClassificationSafty and PrivacyTransformerPrompt EngineeringImage

🎯 What it does: Utilizing visual prompting to reshape pre-trained models, using them as teacher models, and combining with the PATE framework for differential privacy training to construct a high-accuracy differential privacy image classifier.

Exploring the Sim2Real Gap Using Digital Twins

Sruthi Sudhakar (Columbia University), Vibhav Vineet (Microsoft Research)

CodeObject DetectionSegmentationConvolutional Neural NetworkImage

🎯 What it does: Constructed two digital twin datasets, YCB-Real and YCB-Synthetic, systematically introducing five types of defects (noise, holes, texture blur, baked lighting, ambient lighting) into 3D models, and evaluated the impact of these defects on model performance in object detection and instance segmentation tasks, while providing a cost-benefit analysis of artist repair time and model accuracy.

Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives

Haoning Wu (Nanyang Technological University), Weisi Lin (Nanyang Technological University)

CodeRecommendation SystemTransformerSupervised Fine-TuningVideo

🎯 What it does: This study constructed the DIVIDE-3k user-generated content video quality database and proposed two no-reference video quality assessment methods, DOVER and DOVER++, based on the separation of aesthetic and technical perspectives.

Extensible and Efficient Proxy for Neural Architecture Search

Yuhong Li (University of Illinois), Deming Chen (University of Illinois)

CodeNeural Architecture SearchImage

🎯 What it does: This paper proposes a scalable low-cost proxy (Eproxy) and discrete proxy search (DPS) for rapid evaluation of network architectures across different NAS search spaces and multimodal settings.

FaceCLIPNeRF: Text-driven 3D Face Manipulation using Deformable Neural Radiance Fields

Sungwon Hwang (Korea Advanced Institute of Science and Technology), Jaegul Choo (Korea Advanced Institute of Science and Technology)

CodeGenerationData SynthesisNeural Radiance FieldContrastive LearningVideoText

🎯 What it does: This paper presents FaceCLIPNeRF, a text-driven 3D avatar NeRF deformation and rendering framework that enables automated editing of facial expressions, emotions, and other attributes while maintaining facial identity and high-quality rendering.

Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimation

Liwen Wu (University of California San Diego), Ravi Ramamoorthi (University of California San Diego)

CodeComputational EfficiencyImage

🎯 What it does: This paper proposes a new inverse path tracing methodβ€”Factorized Inverse Path Tracing (FIPT)β€”for efficiently and accurately estimating material properties and light distribution in indoor scenes.

FACTS: First Amplify Correlations and Then Slice to Discover Bias

Sriram Yenamandra (Georgia Institute of Technology), Judy Hoffman (Georgia Institute of Technology)

CodeClassificationConvolutional Neural NetworkSupervised Fine-TuningContrastive LearningImage

🎯 What it does: This paper proposes a method for automatically identifying subsets of bias conflicts in visual datasets caused by spurious correlations, called FACTS;

Fan-Beam Binarization Difference Projection (FB-BDP): A Novel Local Object Descriptor for Fine-Grained Leaf Image Retrieval

Xin Chen (Griffith University), Yongsheng Gao (Griffith University)

CodeRetrievalImageAgriculture Related

🎯 What it does: This paper proposes a new local descriptor - Fan Beam Binary Differential Projection (FB-BDP) for fine-grained leaf image retrieval;

Fast Full-frame Video Stabilization with Iterative Optimization

Weiyue Zhao (Huazhong University of Science and Technology), Zhiguo Cao (Huazhong University of Science and Technology)

CodeRestorationOptimizationOptical FlowVideo

🎯 What it does: A full-frame video stabilization method based on iterative optimization is proposed, which includes two main modules: motion trajectory smoothing and full-frame outpainting.

Fast Neural Scene Flow

Xueqian Li (University of Adelaide), Simon Lucey (University of Adelaide)

CodeAutonomous DrivingOptimizationComputational EfficiencyNeural Radiance FieldOptical FlowPoint Cloud

🎯 What it does: A runtime optimization method for neural scene flow estimation based on distance transformation is implemented, which achieves real-time performance on dense point clouds without the need for training.

FB-BEV: BEV Representation from Forward-Backward View Transformations

Zhiqi Li (Nanjing University), Jose M. Alvarez (NVIDIA)

CodeObject DetectionAutonomous DrivingConvolutional Neural NetworkSupervised Fine-TuningImage

🎯 What it does: A front-and-back projection joint BEV transformation module FB-BEV is proposed to generate denser and higher-quality bird's-eye view features for multi-camera 3D detection.

FCCNs: Fully Complex-valued Convolutional Networks using Complex-valued Color Model and Loss Function

Saurabh Yadav (Indraprastha Institute of Information Technology Delhi), Koteswar Rao Jerripothula (Indraprastha Institute of Information Technology Delhi)

CodeClassificationConvolutional Neural NetworkImage

🎯 What it does: A Full Complex-valued Convolutional Network (FCCN) is proposed, achieving a complete flow of complex numerical information from input to output.

Feature Proliferation -- the "Cancer" in StyleGAN and its Treatments

Shuang Song (Cardiff University), Yipeng Qin (Cardiff University)

CodeRestorationGenerationData SynthesisGenerative Adversarial NetworkImage

🎯 What it does: A post-processing method is proposed to eliminate artifacts in StyleGAN synthesized images by identifying and scaling 'cancer' features, enhancing image quality without sacrificing diversity.

FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning

Guangyu Sun (University of Central Florida), Chen Chen (University of Pittsburgh)

CodeClassificationFederated LearningTransformerImage

🎯 What it does: This paper studies partial model personalization of Vision Transformers (ViT) in federated learning. It first identifies that the self-attention layers and classification heads are the most sensitive layers through empirical research, and then proposes the FedPerfix method, which inserts a Prefix plugin into the global self-attention layer and uses parallel adapters for stable initialization, thereby achieving a mix of local and global attention learning.

Few Shot Font Generation Via Transferring Similarity Guided Global Style and Quantization Local Style

Wei Pan (Wuhan University of Technology), Shilin Li (Wuhan University of Technology)

CodeGenerationData SynthesisTransformerAuto EncoderContrastive LearningImage

🎯 What it does: This paper proposes a few-shot font generation method that combines global and local style aggregation;

FineRecon: Depth-aware Feed-forward Network for Detailed 3D Reconstruction

Noah Stier (Apple), Baptiste Angles (Apple)

CodeRestorationSegmentationDepth EstimationConvolutional Neural NetworkPoint Cloud

🎯 What it does: An end-to-end deep learning framework called FineRecon is proposed, which directly predicts the scene TSDF from multi-view images with known poses, achieving high-fidelity 3D reconstruction.

FLIP: Cross-domain Face Anti-spoofing with Language Guidance

Koushik Srivatsan (Mohamed Bin Zayed University of Artificial Intelligence), Karthik Nandakumar (Mohamed Bin Zayed University of Artificial Intelligence)

CodeRecognitionDomain AdaptationTransformerVision Language ModelContrastive LearningImageMultimodality

🎯 What it does: This paper studies a cross-domain face spoofing detection method based on a vision-language pre-training model.

Focal Network for Image Restoration

Yuning Cui (Technical University of Munich), Alois Knoll (Technical University of Munich)

CodeRestorationConvolutional Neural NetworkImage

🎯 What it does: An efficient image restoration network named FocalNet is proposed, primarily targeting tasks such as dehazing, snow removal, and deblurring.

Focus on Your Target: A Dual Teacher-Student Framework for Domain-Adaptive Semantic Segmentation

Xinyue Huo (University of Science and Technology of China), Qi Tian (Huawei Inc.)

CodeSegmentationDomain AdaptationAutonomous DrivingImage

🎯 What it does: Proposes a dual teacher-student framework and introduces a bidirectional learning strategy, separating the two capabilities of learning and adaptation, enhancing the performance of unsupervised domain adaptive semantic segmentation.

Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked Autoencoders

Jie Cheng (Hong Kong University of Science and Technology), Ming Liu (Hong Kong University of Science and Technology)

CodeAutonomous DrivingTransformerAuto EncoderPoint CloudBenchmark

🎯 What it does: A self-supervised pre-training framework called Forecast-MAE based on Masked Autoencoder is proposed for traffic motion prediction tasks.

Foreground and Text-lines Aware Document Image Rectification

Heng Li (PengCheng Laboratory), Qianjin Xiang (PengCheng Laboratory)

CodeRecognitionRestorationConvolutional Neural NetworkTransformerImageBenchmark

🎯 What it does: This paper proposes a cross-attention fusion framework based on foreground and text lines to achieve geometric distortion removal of document images and improve readability.

Foreground-Background Separation through Concept Distillation from Generative Image Foundation Models

Mischa Dombrowski (Friedrich-Alexander-UniversitΓ€t Erlangen-NΓΌrnberg), Bernhard Kainz (Imperial College London)

CodeSegmentationGenerationDiffusion modelImageBiomedical Data

🎯 What it does: Automatically generate foreground-background segmentation masks through a pre-trained latent diffusion model and text prompts, achieving unsupervised segmentation model training.

FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object Segmentation

Tianyi Shi (Huazhong University of Science and Technology), Xin Yang (Huazhong University of Science and Technology)

CodeSegmentationConvolutional Neural NetworkContrastive LearningImage

🎯 What it does: This paper proposes an unsupervised curve structure segmentation method called FreeCOS, which extracts robust features from fractals and unlabeled images through self-supervised learning to achieve segmentation of curved objects such as blood vessels and cracks.

From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels

Zhendong Yang (Tsinghua University), Yu Li (International Digital Economy Academy)

CodeObject DetectionKnowledge DistillationConvolutional Neural NetworkTransformerImage

🎯 What it does: This paper proposes two unified knowledge distillation methods: Normalized KD (NKD) and Universal Self-Knowledge Distillation (USKD), which are used for teacher-assisted and teacher-free training scenarios, respectively.

From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal

Yun Guo (Huazhong University of Science and Technology), Luxin Yan (Huazhong University of Science and Technology)

CodeRestorationObject DetectionSegmentationTransformerImageVideoBenchmark

🎯 What it does: A large-scale high-quality real rain dataset, LHP-Rain, has been constructed, and the RLRTR video de-raining and SCD-Former single image de-raining models have been proposed.

GACE: Geometry Aware Confidence Enhancement for Black-Box 3D Object Detectors on LiDAR-Data

David Schinagl (Graz University of Technology), Horst Bischof (Graz University of Technology)

CodeObject DetectionAutonomous DrivingPoint Cloud

🎯 What it does: Proposes the GACE method, which performs geometry information-driven post-processing on the confidence estimation of black-box LiDAR 3D detectors to enhance detection performance.

GAFlow: Incorporating Gaussian Attention into Optical Flow

Ao Luo (Megvii Technology), Shuaicheng Liu (University of Electronic Science and Technology of China)

CodeTransformerOptical FlowImageVideo

🎯 What it does: This paper proposes the GAFlow framework, which introduces a learnable Gaussian attention module in optical flow estimation, used to enhance the local discriminability of feature representations (Gaussian-Constrained Layer, GCL) and the motion affinity during the matching process (Gaussian-Guided Attention Module, GGAM).

GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo Labelers

Tuan Duc Ngo (VinAI Research), Khoi Nguyen (VinAI Research)

CodeObject DetectionSegmentationPoint Cloud

🎯 What it does: This paper proposes the GaPro method, which utilizes axis-aligned 3D bounding box supervision to generate pseudo-instance masks through Gaussian processes, and uses these to train a 3D point cloud instance segmentation network.

GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes

Chaoqiang Zhao (East China University of Science and Technology), Stefano Mattoccia (University of Bologna)

CodeDepth EstimationKnowledge DistillationTransformerSimultaneous Localization and MappingImage

🎯 What it does: The GasMono framework is proposed to address the issues of large rotations and low texture in indoor scenes through geometric-assisted self-supervised monocular depth estimation.

GEDepth: Ground Embedding for Monocular Depth Estimation

Xiaodong Yang (QCraft), Zhe Ren

CodeDepth EstimationAutonomous DrivingConvolutional Neural NetworkTransformerImage

🎯 What it does: This paper proposes a ground-embedded module GEDepth, which decouples camera parameters and image features to enhance the generalization ability of monocular depth estimation.

General Image-to-Image Translation with One-Shot Image Guidance

Bin Cheng (NetEase Games AI Lab), Yue Lin (NetEase Games AI Lab)

CodeImage TranslationGenerationDiffusion modelImage

🎯 What it does: This paper proposes a framework called Visual Concept Translator (VCT) for general image-to-image translation tasks given only a reference image, capable of transferring visual concepts from the reference image while preserving the content of the source image.

General Planar Motion from a Pair of 3D Correspondences

Juan Carlos Dibene (Stevens Institute of Technology), Enrique Dunn (Stevens Institute of Technology)

CodePose EstimationAutonomous DrivingSimultaneous Localization and MappingPoint Cloud

🎯 What it does: A geometric closed-form solver based on two 3D-3D corresponding points is proposed to estimate the relative pose (5 degrees of freedom) of the camera and the motion plane under unknown motion planes.

Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization

Xiran Wang (Nanjing University), Yinghuan Shi (Nanjing University)

CodeDomain AdaptationMeta LearningConvolutional Neural NetworkImage

🎯 What it does: This paper proposes a dual meta-learning framework MEDIC for open set domain generalization, which jointly learns model parameters through domain-level and class-level gradient matching, and constructs decision boundaries for each known class using multiple binary classifiers.

Generalized Differentiable RANSAC

Tong Wei (Czech Technical University in Prague), Daniel Barath (ETH Zurich)

CodeOptimizationReinforcement LearningPoint Cloud

🎯 What it does: A differentiable RANSAC framework, βˆ‡-RANSAC, is proposed and implemented, capable of learning matching confidence, sampling distribution, and minimum solvers, achieving end-to-end training from feature matching to model estimation.

Generalized Lightness Adaptation with Channel Selective Normalization

Mingde Yao (University of Science and Technology of China), Zhiwei Xiong (University of Science and Technology of China)

CodeImage TranslationImage HarmonizationRestorationImage

🎯 What it does: A general photometric adaptive Channel Selective Normalization (CSNorm) module is proposed, which can effectively enhance, color-correct, and beautify images under unknown photometric conditions after being trained with a single photometric condition.

Generating Instance-level Prompts for Rehearsal-free Continual Learning

Dahuin Jung (Seoul National University), Hwanjun Song (Amazon Web Services)

CodeDomain AdaptationTransformerPrompt EngineeringImage

🎯 What it does: A no-pool domain adaptive prompt (DAP) framework is proposed, capable of generating prompts instantaneously at the instance level to adjust the frozen ViT backbone, enabling replay-free continual learning.

Generative Gradient Inversion via Over-Parameterized Networks in Federated Learning

Chi Zhang (Institute of High Performance Computing), Yong Liu (Institute of High Performance Computing)

CodeRestorationGenerationFederated LearningConvolutional Neural NetworkGenerative Adversarial NetworkImage

🎯 What it does: This study investigates the recovery of high-resolution, large-batch, and complex image samples through gradient inversion in federated learning, proposing a CI-Net generator based on over-parameterized convolutional networks.

Generative Novel View Synthesis with 3D-Aware Diffusion Models

Eric R. Chan (Stanford University), Gordon Wetzstein (NVIDIA)

CodeGenerationData SynthesisDiffusion modelImage

🎯 What it does: A new 3D-aware view synthesis framework based on diffusion models is proposed, capable of generating diverse and geometrically consistent novel views from a single or a few input images, and supports autoregressive long sequence generation.

Generative Prompt Model for Weakly Supervised Object Localization

Yuzhong Zhao (University of Chinese Academy of Sciences), Fang Wan (University of Chinese Academy of Sciences)

CodeObject DetectionTransformerVision Language ModelDiffusion modelImage

🎯 What it does: A generative prompt model called GenPromp is proposed, redefining the weakly supervised object localization problem as a conditional image denoising task. By learning category representative prompt embeddings and fusing them with CLIP discriminative embeddings, high-quality localization maps are generated using multi-scale cross-attention.

Geometrized Transformer for Self-Supervised Homography Estimation

Jiazhen Liu (Renmin University of China), Xirong Li (Renmin University of China)

CodeTransformerImage

🎯 What it does: Proposes GeoFormer, a detector-free homography estimation method based on Transformer.

GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation

Siyu Ren (City University of Hong Kong), Wenping Wang (Texas A&M University)

CodeGenerationOptimizationGraph Neural NetworkPoint CloudMesh

🎯 What it does: A learning-based surface reconstruction framework called GeoUDF is proposed, which can directly reconstruct closed or non-closed 3D surfaces from sparse point clouds and generate high-quality triangular meshes.

GePSAn: Generative Procedure Step Anticipation in Cooking Videos

Mohamed A. Abdelsalam (Samsung AI Centre), Afsaneh Fazly (Samsung AI Centre)

CodeGenerationDomain AdaptationTransformerAuto EncoderVideoTextMultimodality

🎯 What it does: This paper proposes a generative model named GEPSAN, which predicts multiple possible next steps from procedural videos (using cooking as an example) and achieves zero-shot transfer under video input.

Get the Best of Both Worlds: Improving Accuracy and Transferability by Grassmann Class Representation

Haoqi Wang (EPFL), Wayne Zhang (SenseTime Research)

CodeClassificationRepresentation LearningConvolutional Neural NetworkSupervised Fine-TuningImage

🎯 What it does: Generalize the category vector to a linear subspace and use subspace projection in the final fully connected layer to compute logits, constructing the Grassmann Class Representation (GCR);

GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization

Hao Fang (Harbin Institute of Technology), Shu-Tao Xia (Tsinghua University)

CodeGenerationFederated LearningAdversarial AttackGenerative Adversarial NetworkImage

🎯 What it does: A gradient inversion attack method based on Generative Adversarial Networks (GAN) is proposed (GIFD), which recovers the private data corresponding to the uploaded gradients in federated learning by searching the feature domain of the generator layer by layer.

GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video

Bruce X.B. Yu (Hong Kong Polytechnic University), Chang Wen Chen (Hong Kong Polytechnic University)

CodePose EstimationGraph Neural NetworkVideo

🎯 What it does: A global-local adaptive graph convolutional network (GLA-GCN) is proposed for 3D human pose estimation in monocular videos, capturing spatiotemporal structures in the global layer and performing fine regression for each joint in the local layer.

Global Features are All You Need for Image Retrieval and Reranking

Shihao Shao (Peking University), Bingyi Cao (Google Research)

CodeRetrievalConvolutional Neural NetworkContrastive LearningImage

🎯 What it does: Proposes the SuperGlobal system, which utilizes improved global features to complete image retrieval and re-ranking, completely independent of local features;

Global Perception Based Autoregressive Neural Processes

Jinyang Tai (Shanghai University)

CodeGenerationData SynthesisMeta LearningRecurrent Neural NetworkTransformerAuto EncoderImageTime Series

🎯 What it does: A self-autoregressive neural process framework AENPs and CAENPs is proposed, improving the latent distribution and deterministic paths of NPs, allowing the model to better capture the global and local relationships of contextual sample points.

Gloss-Free Sign Language Translation: Improving from Visual-Language Pretraining

Benjia Zhou (MUST), Du Zhang (MUST)

CodeRecognitionGenerationTransformerVision Language ModelContrastive LearningVideoText

🎯 What it does: This paper proposes a gloss-free supervised sign language translation framework GFSLT-VLP, which utilizes visual-language pre-training (VLP) and masked self-supervised learning to enhance the language-guided representation of the visual encoder, thereby achieving end-to-end translation from sign language to text.

GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation

Can Qin (Northeastern University), Ran Xu (Salesforce AI Research)

CodeGenerationData SynthesisTransformerDiffusion modelAuto EncoderGenerative Adversarial NetworkImageMultimodalityAudio

🎯 What it does: This paper proposes the GlueGen framework, which utilizes GlueNet to achieve seamless alignment of different conditional encoders (such as multilingual and audio) with existing stable diffusion models, enabling X-to-image generation.

Going Beyond Nouns With Vision & Language Models Using Synthetic Data

Paola Cascante-Bonilla (Rice University), Leonid Karlinsky (IBM Research)

CodeData SynthesisDomain AdaptationTransformerSupervised Fine-TuningVision Language ModelImageTextMultimodality

🎯 What it does: By generating millions of synthetic image-text pairs (SyViC dataset) and combining techniques such as parameter-efficient fine-tuning (LoRA), domain-adaptive style transfer, and long text chunking, we fine-tune existing large-scale vision-language models (such as CLIP, CyCLIP) to enhance their understanding of visual language concepts beyond nouns (attributes, relationships, states) and their ability for compositional reasoning.

Going Denser with Open-Vocabulary Part Segmentation

Peize Sun (University of Hong Kong), Zhicheng Yan (University of Hong Kong)

CodeObject DetectionSegmentationTransformerContrastive LearningImage

🎯 What it does: A detector capable of performing object and part segmentation at open vocabulary and multi-level fine granularity is proposed;

Gramian Attention Heads are Strong yet Efficient Vision Learners

Jongbin Ryu (Ajou University), Jongwoo Lim (Seoul National University)

CodeClassificationSegmentationConvolutional Neural NetworkTransformerSupervised Fine-TuningImage

🎯 What it does: In visual classification tasks, a multi-head lightweight classifier is introduced, and Gramian attention is used to enhance class labels, improving the model's expressive capability.

Graph Matching with Bi-level Noisy Correspondence

Yijie Lin (Sichuan University), Xi Peng (Sichuan University)

CodeOptimizationKnowledge DistillationRepresentation LearningGraph Neural NetworkContrastive LearningGraph

🎯 What it does: The Bi-Level Noisy Correspondence (BNC) problem in graph matching is proposed, and the COMMON method is introduced to achieve robust matching through contrastive learning and momentum distillation.

GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentation

Jiewen Yang (Hong Kong University of Science and Technology), Xiaomeng Li (Hong Kong University of Science and Technology)

CodeSegmentationDomain AdaptationGraph Neural NetworkContrastive LearningVideoBiomedical DataUltrasound

🎯 What it does: A graph-based unsupervised domain adaptation method called GraphEcho is proposed for structural segmentation of cardiac ultrasound videos.

GridMM: Grid Memory Map for Vision-and-Language Navigation

Zihan Wang (Chinese Academy of Sciences), Shuqiang Jiang (Chinese Academy of Sciences)

CodeTransformerReinforcement LearningVision Language ModelMultimodality

🎯 What it does: A dynamic growth grid memory map (GridMM) is proposed to structurally record historical environments in visual and language navigation tasks, and an instruction-related aggregation method is designed to capture fine-grained visual cues.

GridPull: Towards Scalability in Learning Implicit Representations from 3D Point Clouds

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

CodeOptimizationRepresentation LearningPoint Cloud

🎯 What it does: The GridPull method is proposed, which achieves efficient surface reconstruction of large-scale point clouds by directly optimizing the distance field on a discrete grid, avoiding the use of neural networks.

Grounded Entity-Landmark Adaptive Pre-Training for Vision-and-Language Navigation

Yibo Cui (Defense Innovation Institute), Erwei Yin (Defense Innovation Institute)

CodeTransformerVision Language ModelMultimodality

🎯 What it does: By constructing a high-quality entity-landmark alignment dataset GEL-R2R, and based on this, conducting three entity-landmark level adaptive pre-training tasks (entity phrase prediction, landmark box prediction, semantic alignment) for the VLN pre-training model, the fine-grained cross-modal alignment ability of visual and language navigation is enhanced.

Grounding 3D Object Affordance from 2D Interactions in Images

Yuhang Yang (University of Science and Technology of China), Zheng-Jun Zha (University of Science and Technology of China)

CodeRecognitionObject DetectionRobotic IntelligenceConvolutional Neural NetworkTransformerImageMultimodalityPoint Cloud

🎯 What it does: Proposes to locate interactive areas in 3D point clouds from 2D interactive images, addressing the problem of operability recognition for 3D objects.

Group Pose: A Simple Baseline for End-to-End Multi-Person Pose Estimation

Huan Liu (Beijing Jiaotong University), Jingdong Wang (Baidu)

CodePose EstimationTransformerImage

🎯 What it does: A simple end-to-end multi-person pose estimation framework called Group Pose is proposed.

H3WB: Human3.6M 3D WholeBody Dataset and Benchmark

Yue Zhu (Ecole des Ponts), David Picard (Ecole des Ponts)

CodePose EstimationTransformerDiffusion modelAuto EncoderImageBenchmark

🎯 What it does: The Human3.6M 3D WholeBody (H3WB) dataset is proposed, and based on this, three benchmark tasks for 3D full-body pose estimation are defined; multi-stage baseline results are also provided.

HDG-ODE: A Hierarchical Continuous-Time Model for Human Pose Forecasting

Yucheng Xing (Stony Brook University), Xin Wang (Stony Brook University)

CodePose EstimationGraph Neural NetworkTime SeriesSequentialOrdinary Differential Equation

🎯 What it does: This study proposes a continuous-time model based on hierarchical dynamic graph ODE for predicting future 3D human poses from multi-person 2D skeleton sequences.

Heterogeneous Forgetting Compensation for Class-Incremental Learning

Jiahua Dong (State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences), Gan Sun (State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences)

CodeClassificationKnowledge DistillationTransformerImage

🎯 What it does: The Heterogeneous Forgetting Compensation (HFC) model is proposed in class-incremental learning to address the different forgetting rates of old classes at both the representation and gradient levels.

Hiding Visual Information via Obfuscating Adversarial Perturbations

Zhigang Su (Xidian University), Xinbo Gao (Chongqing University of Posts and Telecommunications)

CodeClassificationRecognitionAdversarial AttackConvolutional Neural NetworkGenerative Adversarial NetworkImage

🎯 What it does: A visual information hiding method based on Type-I adversarial attacks (AVIH) is designed to completely obscure the visual content of images without altering the service model, while maintaining the original functionalities (such as face recognition and classification).