arXivSub Start free trial

ECCV 2024 Papers with Code β€” Page 9

European Conference on Computer Vision Β· 980 papers

Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights

Yan Hao (EPFL), Olga Fink (EPFL)

CodeObject DetectionDomain AdaptationConvolutional Neural NetworkImage

🎯 What it does: For target detection domain adaptation when source data is unavailable, a simpler self-training strategy is proposed and its effectiveness is evaluated against existing complex methods.

SINDER: Repairing the Singular Defects of DINOv2

Haoqi Wang (EPFL), Mathieu Salzmann (EPFL)

CodeClassificationRestorationSegmentationTransformerSupervised Fine-TuningImage

🎯 What it does: Investigated and repaired the single-value defect in the DINOv2 Vision Transformer, proposing the SINDER method which fixes the defect by fine-tuning singular values and incorporating smooth regularization.

SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers

Nanye Ma (New York University), Saining Xie (New York University)

CodeGenerationTransformerDiffusion modelFlow-based ModelImageStochastic Differential EquationOrdinary Differential Equation

🎯 What it does: Building upon Diffusion Transformers, we propose Scalable Interpolant Transformers (SiT), incorporating improvements such as interpolators, continuous time training, velocity prediction, and adjustable noise coefficients to create more flexible flow/diffusion generation models, achieving superior FID results on ImageNet 256Γ—256 and 512Γ—512.

Six-Point Method for Multi-Camera Systems with Reduced Solution Space

Banglei Guan (National University of Defense Technology), Laurent Kneip (ShanghaiTech University)

CodePose EstimationImage

🎯 What it does: Proposed a minimal solver for solving relative pose in multi-camera systems using six point correspondences (PC), enabling 6DOF pose estimation;

Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures

Yannick Kirchhoff (German Cancer Research Center), Klaus H. Maier-Hein

CodeSegmentationComputational EfficiencyConvolutional Neural NetworkImageBiomedical Data

🎯 What it does: Propose Skeleton Recall Loss, a loss function that enforces connectivity constraints on thin tubular structures through a precomputed tubed skeleton.

Skeleton-based Group Activity Recognition via Spatial-Temporal Panoramic Graph

Zhengcen Li (Harbin Institute of Technology), Jingyong Su (Harbin Institute of Technology)

CodeRecognitionObject TrackingPose EstimationGraph Neural NetworkSupervised Fine-TuningVideoGraph

🎯 What it does: Propose a panoramic graph structure combining multi-person human skeletons and object key points, and design a multi-scale spatiotemporal GCN (MP-GCN) for collective action recognition.

Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation

Yingshan Chang (Carnegie Mellon University), Feng Gao (Amazon)

CodeGenerationConvolutional Neural NetworkTransformerDiffusion modelImageTextMultimodality

🎯 What it does: This paper defines and quantifies the completeness and balance of the 'role-filler' relationship in text-image generation, systematically investigates the impact of data distribution skew on model generalization using synthetic and real images (What'sUp benchmark), and proposes two types of statistical metrics for visual and language spaces.

SkyMask: Attack-agnostic Robust Federated Learning with Fine-grained Learnable Masks

Peishen Yan (Shanghai Jiao Tong University), Haibing Guan (Shanghai Jiao Tong University)

CodeFederated LearningConvolutional Neural NetworkImage

🎯 What it does: Propose SkyMask, a federated learning framework that detects and defends against Byzantine attacks at the server side by utilizing learnable fine-grained masks.

SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic

Kashyap Chitta (University of TΓΌbingen), Andreas Geiger (University of TΓΌbingen)

CodeAutonomous DrivingConvolutional Neural NetworkTransformerDiffusion modelAuto Encoder

🎯 What it does: This paper proposes SLEDGE, a generative model-based and rule-driven traffic driving environment synthesis and simulation framework;

SLIM: Spuriousness Mitigation with Minimal Human Annotations

Xiwei Xuan (University of California, Davis), Kwan-Liu Ma (University of California, Davis)

CodeClassificationDomain AdaptationConvolutional Neural NetworkImage

🎯 What it does: Propose the SLIM method, which enhances model robustness against spuriousness by constructing an attention space, using minimal manual attention annotations, and selecting feature-balanced data.

SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow

Yuanzhi Zhu (ETH Zurich), Qiang Liu (UT Austin)

CodeGenerationKnowledge DistillationFlow-based ModelRectified FlowImage

🎯 What it does: Develop the SlimFlow framework to train smaller, faster inference one-step diffusion models

SMFANet: A Lightweight Self-Modulation Feature Aggregation Network for Efficient Image Super-Resolution

mingjun zheng (Nanjing University of Science and Technology), Jinshan Pan (Nanjing University of Science and Technology)

CodeSuper ResolutionConvolutional Neural NetworkImage

🎯 What it does: Propose a lightweight self-modulated feature aggregation network, SMFANet, for efficient image super-resolution.

SMILe: Leveraging Submodular Mutual Information For Robust Few-Shot Object Detection

Anay Majee (University of Texas at Dallas), Rishabh Iyer (University of Texas at Dallas)

CodeObject DetectionImage

🎯 What it does: Propose a loss framework called SMILe based on submodular mutual information and total submodular information, specifically designed to address class confusion and catastrophic forgetting issues in few-shot object detection.

SNeRV: Spectra-preserving Neural Representation for Video

Jina Kim (Ewha Womans University), Jewon Kang

CodeRestorationCompressionRepresentation LearningNeural Radiance FieldVideo

🎯 What it does: Proposed SNeRV, which utilizes discrete wavelet transform (DWT) to separate low-frequency and high-frequency components, encodes only the low-frequency components, and reconstructs high-frequency details through MFU/HFR. Further, it extends the time-domain DWT to capture motion, achieving high-quality reconstruction of video implicit representations.

SNP: Structured Neuron-level Pruning to Preserve Attention Scores

KyungHwan Shim, Shinkook Choi (Nota Inc.)

CodeClassificationComputational EfficiencyTransformerImage

🎯 What it does: Propose a graph-aware neuron-level pruning method called SNP to compress and accelerate ViT models while maintaining attention scores.

Snuffy: Efficient Whole Slide Image Classifier

Hossein Jafarinia (Sharif University of Technology), Mohammad Hossein Rohban (Sharif University of Technology)

CodeClassificationComputational EfficiencyRepresentation LearningTransformerSupervised Fine-TuningContrastive LearningBiomedical Data

🎯 What it does: Proposed a MIL-pooling architecture named Snuffy, which utilizes sparse Transformers for efficient classification of whole slide images (WSI), and employs self-supervised pre-training and Adapter for few-shot fine-tuning.

Soft Prompt Generation for Domain Generalization

Shuanghao Bai (Xi'an Jiaotong University), Badong Chen (Xi'an Jiaotong University)

CodeDomain AdaptationRepresentation LearningTransformerPrompt EngineeringVision Language ModelGenerative Adversarial NetworkImageTextMultimodality

🎯 What it does: Propose a soft prompt generation method based on a generative model (SPG), which first learns domain-level soft prompt labels and then uses a conditional GAN (CGAN) to generate instance-level soft prompts for each sample, thereby improving the performance of vision-language models (e.g., CLIP) in domain generalization tasks.

Solving Motion Planning Tasks with a Scalable Generative Model

Yihan Hu (Horizon Robotics Inc.), Qiang Liu (Horizon Robotics Inc.)

CodeAutonomous DrivingRecurrent Neural NetworkTransformerWorld ModelSequential

🎯 What it does: Propose a unified motion planning framework called GUMP based on generative models, which can learn driving scene dynamics, generate diverse future trajectories, and construct new scenarios under different conditions;

Source Prompt Disentangled Inversion for Boosting Image Editability with Diffusion Models

Ruibin Li (Hong Kong Polytechnic University), Lei Zhang (Hong Kong Polytechnic University)

CodeGenerationDiffusion modelImage

🎯 What it does: Design a source prompt decoupling inversion method called SPDInv to enhance the editability of text-driven image editing based on diffusion models.

Source-Free Domain-Invariant Performance Prediction

Ekaterina Khramtsova (University of Queensland), Mathieu Salzmann (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne)

CodeDomain AdaptationScore-based ModelImage

🎯 What it does: Propose a domain-invariant performance prediction method that utilizes only the pre-trained model without relying on source data

SPARO: Selective Attention for Robust and Compositional Transformer Encodings for Vision

Ankit Vani (Mila Universite De Montreal), Aaron Courville (Mila Universite De Montreal)

CodeClassificationRetrievalRepresentation LearningTransformerVision Language ModelContrastive LearningImageText

🎯 What it does: Propose Sparo, replacing the Transformer's end to generate concept-divided slots, enhancing CLIP/DINO representation learning.

Sparse Beats Dense: Rethinking Supervision in Radar-Camera Depth Completion

Huadong Li (MEGVII Technology), Renhe Ji (MEGVII Technology)

CodeDepth EstimationAutonomous DrivingConvolutional Neural NetworkTransformerSupervised Fine-TuningImageMultimodalityPoint Cloud

🎯 What it does: Propose a Disruption-Compensation framework that reconstructs depth maps using sparse radar and camera data. By disrupting and compensating for the stripe-like scanning patterns (LiDAR Distribution Leakage, LDL) that emerge under sparse LiDAR supervision, the method significantly enhances depth prediction quality.

SpatialFormer: Towards Generalizable Vision Transformers with Explicit Spatial Understanding

Han Xiao (Tsinghua University), Jiwen Lu (Tsinghua University)

CodeClassificationObject DetectionSegmentationTransformerImage

🎯 What it does: Propose SpatialFormer, a decoder-only visual Transformer that achieves explicit spatial understanding of images through adaptive spatial tokens and bidirectional cross-attention, which can be directly transferred to multiple tasks such as classification, detection, and segmentation.

Spatially-Variant Degradation Model for Dataset-free Super-resolution

SHAOJIE GUO, Yan Wang (East China Normal University)

CodeRestorationSuper ResolutionConvolutional Neural NetworkImageStochastic Differential Equation

🎯 What it does: Proposed a dataset-agnostic spatially varying degradation model for blind image super-resolution, capable of learning independent degradation kernels for each pixel in the image.

Spherical Linear Interpolation and Text-Anchoring for Zero-shot Composed Image Retrieval

Young Kyun Jang (Meta AI), Ser-Nam Lim (University of Central Florida)

CodeRetrievalSupervised Fine-TuningVision Language ModelContrastive LearningMultimodality

🎯 What it does: Propose a zero-shot compositional image retrieval (ZS-CIR) method based on spherical linear interpolation (Slerp), and introduce a text-anchored fine-tuning (TAT) technique to bridge the modality gap between images and text, achieving efficient retrieval without manual annotation.

Spiking Wavelet Transformer

Yuetong Fang (Hong Kong University of Science and Technology), Renjing Xu (Hong Kong University of Science and Technology)

CodeClassificationRecognitionSpiking Neural NetworkTransformerImage

🎯 What it does: Proposed an attention-free Spiking Wavelet Transformer (SWformer) that combines spiking neural networks with wavelet transforms to achieve event-driven learning of high-frequency features.

SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant

Guohao Sun (Rochester Institute of Technology), Zhiqiang Tao (Rochester Institute of Technology)

CodeRepresentation LearningTransformerVision Language ModelContrastive LearningImageTextMultimodality

🎯 What it does: This paper proposes a self-questioning training method that trains visual-language models to proactively generate high-quality questions related to images after receiving them, thereby enhancing cross-modal alignment and understanding capabilities.

SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning

Mengxin Zheng (University of Central Florida), Xiaofeng Wang (University of Central Florida)

CodeAnomaly DetectionRepresentation LearningAdversarial AttackContrastive LearningImage

🎯 What it does: This paper proposes a complete framework named SSL-Cleanse for detecting and removing backdoors in self-supervised learning (SSL) encoders without relying on downstream labels or training sets.

ST-LLM: Large Language Models Are Effective Temporal Learners

Ruyang Liu (Peking University), Ge Li (Peking University)

CodeRecognitionTransformerLarge Language ModelVideoText

🎯 What it does: Propose the ST-LLM model, which directly inputs all spatial-temporal visual tokens into LLM, achieving efficient video understanding through dynamic masking and global-local input.

STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay

Yu Yongcan (Chinese Academy of Sciences), Jian Liang (Chinese Academy of Sciences)

CodeDomain AdaptationAnomaly DetectionOptimizationImage

🎯 What it does: This study proposes a framework called STAMP for test-time adaptation in the presence of unknown classes, achieving identification and anomaly detection through reliable class-balanced memory and self-weighted entropy minimization.

Statewide Visual Geolocalization in the Wild

Florian Fervers (Fraunhofer Institute of Optronics, System Technologies and Image Exploitation), Rainer Stiefelhagen (Karlsruhe Institute of Technology)

CodePose EstimationRetrievalConvolutional Neural NetworkTransformerContrastive LearningImage

🎯 What it does: Proposes a statewide-level street-level image geolocation method based on multi-scale aerial map matching.

StereoGlue: Joint Feature Matching and Robust Estimation

Daniel Barath (ETH Zurich), Marc Pollefeys (ETH Zurich)

CodePose EstimationImagePoint Cloud

🎯 What it does: Propose a joint feature matching and robust estimation framework called StereoGlue, which generates candidate matches, estimates models, and guides matching through an iterative process using a single-point minimal solver, thereby achieving consistent one-to-one correspondences and model scores.

StoryImager: A Unified and Efficient Framework for Coherent Story Visualization and Completion

Ming Tao (Nanjing University of Posts and Telecommunications), Changsheng Xu (Peng Cheng Laboratory)

CodeGenerationTransformerSupervised Fine-TuningDiffusion modelImageText

🎯 What it does: Proposes a unified and efficient framework for story visualization and completion called StoryImager, supporting bidirectional generation and addressing both story visualization and story completion tasks.

Straightforward Layer-wise Pruning for More Efficient Visual Adaptation

Ruizi Han (Northwest A&F University), Jinglei Tang (Northwest A&F University)

CodeClassificationObject DetectionSegmentationComputational EfficiencyTransformerImageBenchmark

🎯 What it does: Propose a pruning method called SLS based on hierarchical feature clustering, which prunes redundant layers caused by frozen parameters in PETL models during cross-domain tasks;

Strike a Balance in Continual Panoptic Segmentation

Jinpeng Chen (City University of Hong Kong), Sam Kwong (Lingnan University)

CodeSegmentationKnowledge DistillationTransformerImage

🎯 What it does: This paper proposes a new framework called BalConpas for Continual Panoptic Segmentation (CPS), aiming to address core challenges in continual learning, including knowledge retention and adaptation to new knowledge, class distribution imbalance, and misleading effects caused by incomplete annotations of replay samples.

Stripe Observation Guided Inference Cost-free Attention Mechanism

Zhongzhan Huang (Sun Yat-sen University), Liang Lin (Sun Yat-sen University)

CodeClassificationObject DetectionSegmentationComputational EfficiencyConvolutional Neural NetworkTransformerImage

🎯 What it does: Proposes an Attention-like Structural Re-parameterization (ASR) based on Stripe Observation, which uses learnable vectors as inputs to the attention module, making attention values converge to constants after training, thereby achieving structural re-parameterization without additional inference costs.

Style-Extracting Diffusion Models for Semi-Supervised Histopathology Segmentation

Mathias Γ–ttl (Friedrich-Alexander-UniversitΓ€t), Katharina Breininger (Friedrich-Alexander-UniversitΓ€t)

CodeSegmentationGenerationTransformerDiffusion modelAuto EncoderImageBiomedical Data

🎯 What it does: Designed and implemented Style-Extracting Diffusion Models (STEDM), which can generate diverse images by leveraging style information from unseen images given content (e.g., semantic layouts), and applied these synthetic images to semi-supervised histopathological segmentation tasks.

StyleTokenizer: Defining Image Style by a Single Instance for Controlling Diffusion Models

Wen Li (Ant Group), Ming Yang (Ant Group)

CodeGenerationTransformerDiffusion modelContrastive LearningImageTextMultimodality

🎯 What it does: Propose a StyleTokenizer method that maps the style of a single reference image into the text embedding space, enabling single-image style control without training in Stable Diffusion;

Subspace Prototype Guidance for Mitigating Class Imbalance in Point Cloud Semantic Segmentation

Jiawei Han (Beijing Institute of Technology), Guangzhi Chen (Beijing Institute of Technology)

CodeSegmentationContrastive LearningPoint Cloud

🎯 What it does: Propose the Subspace Prototype Guidance (SPG) method, which generates class prototypes through an auxiliary branch in point cloud semantic segmentation and achieves mutual supervision with the main network to alleviate the class imbalance problem.

SUMix: Mixup with Semantic and Uncertain Information

Huafeng Qin (Chongqing Technology and Business University), Xinbo Gao (Chongqing University of Posts and Telecommunications)

CodeClassificationConvolutional Neural NetworkTransformerImage

🎯 What it does: Propose the SUMix method, which learns mixing proportions and models uncertainty in mixed samples to address the label mismatch problem during the Mixup process.

SuperFedNAS: Cost-Efficient Federated Neural Architecture Search for On-Device Inference

Alind Khare (Georgia Institute of Technology), Alexey Tumanov (Cisco Research)

CodeFederated LearningNeural Architecture SearchImageText

🎯 What it does: Proposes the SuperFedNAS method, combining federated learning with super networks to achieve local NAS that requires no additional training after a single training session, enabling rapid fulfillment of diverse device inference objectives.

Surface-Centric Modeling for High-Fidelity Generalizable Neural Surface Reconstruction

Rui Peng (Peking University), Ronggang Wang (University of Birmingham)

CodeConvolutional Neural NetworkNeural Radiance FieldImageBenchmark

🎯 What it does: Proposes SuRF, a neural surface reconstruction framework based on surface centers, which achieves high-fidelity surface reconstruction under sparse multi-view images.

Syn-to-Real Domain Adaptation for Point Cloud Completion via Part-based Approach

Yunseo Yang (KAIST), Kuk-Jin Yoon (KAIST)

CodeRestorationDomain AdaptationTransformerGenerative Adversarial NetworkPoint Cloud

🎯 What it does: A part-based point cloud completion framework is studied, which leverages complete synthetic point clouds and incomplete real point clouds for domain adaptation, enabling the model to complete real-world point clouds without requiring complete real annotations.

Synchronization is All You Need: Exocentric-to-Egocentric Transfer for Temporal Action Segmentation with Unlabeled Synchronized Video Pairs

Camillo Quattrocchi (University of Catania), Giovanni Maria Farinella (University of Catania)

CodeSegmentationDomain AdaptationKnowledge DistillationRepresentation LearningConvolutional Neural NetworkTransformerVideoSequential

🎯 What it does: Studied a method to adapt temporal action segmentation models using synchronized unlabeled exo-ego video pairs.

T-CorresNet: Template Guided 3D Point Cloud Completion with Correspondence Pooling Query Generation Strategy

Fan Duan (Tsinghua University), Li Chen (Tsinghua University)

CodeRestorationGraph Neural NetworkTransformerPoint Cloud

🎯 What it does: Proposes a 3D point cloud completion method based on Gaussian spherical template-guided coarse-to-fine template generation and correspondence-pooling query generator.

T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

Qing Jiang (South China University of Technology), Lei Zhang (South China University of Technology)

CodeObject DetectionTransformerPrompt EngineeringContrastive LearningMultimodality

🎯 What it does: Proposed and implemented T-Rex2, an open-set object detection model that can collaborate through text and visual prompts, supporting multiple prompt methods and achieving zero-shot object detection within a single framework.

Tackling Structural Hallucination in Image Translation with Local Diffusion

Seunghoi Kim (University College London), Daniel Alexander (AstraZeneca)

CodeImage TranslationAnomaly DetectionDiffusion modelImageBiomedical DataMagnetic Resonance Imaging

🎯 What it does: By incorporating a local diffusion process into pre-trained diffusion models, first using PatchCore for OOD region detection, then performing parallel generation (branching) separately on OOD and IND regions, and finally fusing predictions (fusion), thus reducing structural hallucinations in image translation.

TAG: Text Prompt Augmentation for Zero-Shot Out-of-Distribution Detection

Xixi Liu (Chalmers University of Technology), Christopher Zach (Chalmers University of Technology)

CodeAnomaly DetectionPrompt EngineeringMultimodality

🎯 What it does: This paper proposes a zero-shot OOD detection method based on Text Prompt Augmentation (TAG), leveraging CLIP's multimodal features to enhance the separation between ID and OOD samples.

TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting

Jiahe Li (Beihang University), Lin Gu (RIKEN AIP)

CodeGenerationData SynthesisGaussian SplattingVideoPoint Cloud

🎯 What it does: This paper proposes a deformation-driven 3D talking head avatar synthesis framework based on 3D Gaussian scatteringβ€”TalkingGaussianβ€”which can generate realistic talking head videos by applying smooth deformations to persistent Gaussian primitives.

Taming CLIP for Fine-grained and Structured Visual Understanding of Museum Exhibits

Ada-Astrid Balauca (INSAIT, Sofia University), Luc Van Gool (ETH Zurich)

CodeRecognitionTransformerVision Language ModelContrastive LearningImageTabular

🎯 What it does: Studies how to utilize the CLIP model combined with a parsing network to generate structured tabular information from museum exhibit images.

Taming Lookup Tables for Efficient Image Retouching

Sidi Yang (Tsinghua University), Yujiu Yang (University Of Hong Kong)

CodeImage HarmonizationComputational EfficiencyConvolutional Neural NetworkImage

🎯 What it does: Designed and implemented an image enhancement model called ICELUT, which is entirely based on lookup tables (LUTs), eliminating CNN computations to achieve ultra-low-latency inference.

Task-Driven Uncertainty Quantification in Inverse Problems via Conformal Prediction

Jeffrey Wen (Ohio State University), Phillip Schniter

CodeClassificationRestorationFlow-based ModelBiomedical Data

🎯 What it does: This paper proposes a task-driven uncertainty quantification framework based on conformal prediction, for evaluating uncertainty in downstream tasks (e.g., soft output classification) from images recovered with limited measurements.

TCAN: Animating Human Images with Temporally Consistent Pose Guidance using Diffusion Models

Jeongho Kim (KAIST), Jaegul Choo (KAIST)

CodeGenerationPose EstimationConvolutional Neural NetworkTransformerDiffusion modelImageVideo

🎯 What it does: Achieve pose and appearance feature alignment using a frozen pre-trained ControlNet and LoRA, and propose the TCAN framework to realize temporally consistent animation under driven video poses by introducing Temporal ControlNet and Pose-Driven Temperature Map.

Teach CLIP to Develop a Number Sense for Ordinal Regression

Yao DU, Xiaomeng Li (Hong Kong University of Science and Technology)

CodeVision Language ModelContrastive LearningMultimodalityBenchmark

🎯 What it does: Propose NumCLIP, which leverages CLIP's cross-modal knowledge to learn numerical perception and improve ordinal regression performance

Teddy: Efficient Large-Scale Dataset Distillation via Taylor-Approximated Matching

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

CodeComputational EfficiencyKnowledge DistillationImage

🎯 What it does: This paper proposes the Teddy framework, which decouples bi-level optimization through Taylor approximation and pre-caches weak teacher models to achieve efficient training for large-scale dataset distillation.

Temporal As a Plugin: Unsupervised Video Denoising with Pre-Trained Image Denoisers

Zixuan Fu (Nanyang Technological University), Bihan Wen (Nanyang Technological University)

CodeRestorationConvolutional Neural NetworkAuto EncoderVideo

🎯 What it does: Propose an unsupervised video denoising framework called TAP that leverages a pre-trained image denoiser to remove noise from videos without requiring noisy-clean video pairs;

Temporal Event Stereo via Joint Learning with Stereoscopic Flow

Hoonhee Cho (Korea Advanced Institute of Science and Technology), Kuk-Jin Yoon (Korea Advanced Institute of Science and Technology)

CodeDepth EstimationAutonomous DrivingConvolutional Neural NetworkContrastive LearningOptical FlowTime Series

🎯 What it does: This paper proposes a temporal event stereo matching framework that significantly improves the stereo matching accuracy of event cameras by jointly learning stereo flow and stereo matching networks, using features and cost volumes from previous time steps for Warping and fusion.

Temporal-Mapping Photography for Event Cameras

Yuhan Bao (Zhejiang University), Kaiwei Wang (Zhejiang University)

CodeRestorationSuper ResolutionTransformerImageTime Series

🎯 What it does: Proposed a time-mapping photography method based on an event camera (EvTemMap), which gradually increases light transmittance using a variable aperture in static scenes, records the timestamp of the first positive event (IPE) for each pixel, and converts sparse event streams into dense grayscale images.

Temporally Consistent Stereo Matching

Jiaxi Zeng (Beijing Institute of Technology), Yunde Jia (Guangdong Laboratory of Machine Perception and Intelligent Computing)

CodeDepth EstimationRecurrent Neural NetworkContrastive LearningVideo

🎯 What it does: Proposed a stereo matching method called TC-Stereo based on temporal consistency, which utilizes semi-dense disparity projection from previous frames for completion, state fusion, and bidirectional iterative refinement in dual spaces (disparity and disparity gradient).

Text2LiDAR: Text-guided LiDAR Point Clouds Generation via Equirectangular Transformer

Yang Wu, Jian Yang (Nanjing University of Science and Technology)

CodeGenerationData SynthesisAutonomous DrivingTransformerDiffusion modelTextPoint Cloud

🎯 What it does: Proposed Text2LiDAR, a text-controlled LiDAR point cloud generation framework capable of converting natural language descriptions into high-quality, controllable 360° LiDAR data.

Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery

Haiyang Zheng (University of Trento), Zhun Zhong (University of Trento)

CodeClassificationRecognitionLarge Language ModelVision Language ModelContrastive LearningImageTextMultimodalityRetrieval-Augmented Generation

🎯 What it does: Propose a two-stage framework called TextGCD, which first constructs image captions through retrieval-based text generation, and then improves the accuracy of general category discovery by utilizing cross-modal co-teaching and alignment.

Textual-Visual Logic Challenge: Understanding and Reasoning in Text-to-Image Generation

Peixi Xiong (Intel Labs), Nilesh Jain (Intel Labs)

CodeGenerationExplainability and InterpretabilityTransformerLarge Language ModelVision Language ModelGenerative Adversarial NetworkImageTextMultimodality

🎯 What it does: Proposed a logic-rich text-to-image generation task and constructed the TV-Logic dataset along with the baseline UnR-GAN model.

TF-FAS: Twofold-Element Fine-Grained Semantic Guidance for Generalizable Face Anti-Spoofing

Xudong Wang (Xiamen University), Rongrong Ji (Xiamen University)

CodeAnomaly DetectionTransformerPrompt EngineeringVision Language ModelContrastive LearningImageTextMultimodality

🎯 What it does: Propose a multimodal framework named TF-FAS for generalized face anti-spoofing, leveraging two fine-grained semantic guidance mechanisms (content and category) to enhance the model's cross-domain generalization capability.

The All-Seeing Project V2: Towards General Relation Comprehension of the Open World

Weiyun Wang (Fudan University), Jifeng Dai (OpenGVLab, Shanghai AI Laboratory)

CodeRecognitionObject DetectionGenerationTransformerLarge Language ModelSupervised Fine-TuningVision Language ModelImageTextMultimodalityBenchmark

🎯 What it does: This paper proposes the Relation Conversation (ReC) task, constructs a high-quality dataset AS-V2, and designs an evaluation benchmark CRPE. Based on these resources, the All-Seeing Model v2 (ASMv2) was trained, achieving significant improvements in image relation understanding, scene graph generation, and general vision-language tasks.

The Devil is in the Statistics: Mitigating and Exploiting Statistics Difference for Generalizable Semi-supervised Medical Image Segmentation

Muyang Qiu (Nanjing University), Yang Gao (Nanjing University)

CodeSegmentationDomain AdaptationConvolutional Neural NetworkBiomedical DataMagnetic Resonance Imaging

🎯 What it does: Propose a semi-supervised domain generalization framework for medical image segmentation, which utilizes statistical individual branches (SIBs) to obtain reliable pseudo-labels, learns domain-invariant features through statistical aggregation branches (SAB), and simulates unknown domains by introducing multi-level perturbations at both image and feature levels.

The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?

Qinyu Zhao (Australian National University), Stephen Gould (Australian National University)

CodeSafty and PrivacyTransformerSupervised Fine-TuningVision Language ModelMultimodality

🎯 What it does: By performing linear probing on the logit distribution of the first token from large vision-language models (LVLMs), the method determines whether the model should answer a question, thereby identifying unanswerable visual questions, jailbreak attacks, and deceptive questions. During the generation process, a decoding strategy based on the probing results is adopted to enhance the safety and reliability of the generated content.

The Hard Positive Truth about Vision-Language Compositionality

Amita Kamath (University of Washington), Ranjay Krishna (University of Washington)

CodeRetrievalRepresentation LearningTransformerSupervised Fine-TuningVision Language ModelContrastive LearningImageTextMultimodality

🎯 What it does: This paper constructs an evaluation dataset and training set containing hard positive samples to investigate the compositional reasoning ability of vision-language models for image description.

The Sky's the Limit: Relightable Outdoor Scenes via a Sky-pixel Constrained Illumination Prior and Outside-In Visibility

James A D Gardner, William Smith

CodeImage TranslationGenerationNeural Radiance FieldImage

🎯 What it does: This paper proposes the NeuSky method, which utilizes sky pixel constraints and an outward-inward visibility network to achieve inverse rendering for outdoor scenes, decoupling geometry, albedo, distant lighting, and sky visibility.

Think before Placement: Common Sense Enhanced Transformer for Object Placement

Yaxuan Qin (Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences), Xilin Chen (Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences)

CodeGenerationTransformerLarge Language ModelVision Language ModelContrastive LearningMultimodalityChain-of-Thought

🎯 What it does: Propose a 'think before placing' framework named CSENet, which generates location descriptions using a large multimodal model, then predicts the scale and coordinates of foreground objects to achieve object placement that is more semantically and visually consistent.

This Probably Looks Exactly Like That: An Invertible Prototypical Network

Zachariah Carmichael (University of Notre Dame), Walter Scheirer

CodeClassificationGenerationFlow-based ModelImage

🎯 What it does: Propose ProtoFlow, a reversible prototype network that combines conceptual neural networks with flow models to achieve joint generation and prediction, where prototypes represent latent space distributions and can be directly mapped back to the data space for visualization.

Tight and Efficient Upper Bound on Spectral Norm of Convolutional Layers

Ekaterina Grishina (HSE University), Maxim Rakhuba

CodeClassificationOptimizationComputational EfficiencyConvolutional Neural NetworkImage

🎯 What it does: Studied the upper bound of the spectral norm of the Jacobian in convolutional layers, proposed a new upper bound, and proved that this upper bound can be efficiently and differentiably computed during training.

Tiny Models are the Computational Saver for Large Models

Qingyuan Wang (University College Dublin), Deepu John (University College Dublin)

CodeComputational EfficiencyKnowledge DistillationMixture of ExpertsImage

🎯 What it does: Propose TinySaver, a framework that dynamically compresses large models by using a pre-trained mini model for early exit before inference;

TIP: Tabular-Image Pre-training for Multimodal Classification with Incomplete Data

Siyi Du (Imperial College London), Chen Qin (Imperial College London)

CodeClassificationData-Centric LearningTransformerAuto EncoderContrastive LearningImageMultimodalityTabularBiomedical Data

🎯 What it does: Proposed the TIP framework, achieving multi-modal pre-training and downstream classification on tabular and image data with missing values;

To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now

Yimeng Zhang (Michigan State University), Sijia Liu (Michigan State University)

CodeGenerationAdversarial AttackPrompt EngineeringDiffusion modelImageText

🎯 What it does: Proposed a method called UnlearnDiffAtk for generating adversarial prompts based on the internal 'free' classifier of diffusion models, aimed at evaluating the robustness of safety-driven unlearned diffusion models (unlearned DMs).

TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes

Bu Jin (Chinese Academy of Sciences), Hao Zhao (Li Auto)

CodeObject DetectionAutonomous DrivingTransformerLarge Language ModelVision Language ModelImageTextMultimodalityPoint Cloud

🎯 What it does: Proposed the 3D dense description task for outdoor scenes and designed an end-to-end TOD Cap 3 network to output 3D object boxes and natural language descriptions under LiDAR point cloud and panoramic RGB image inputs.

Tokenize Anything via Prompting

Ting Pan, Shiguang Shan

CodeRecognitionSegmentationGenerationTransformerLarge Language ModelPrompt EngineeringVision Language ModelContrastive LearningImageTextMultimodality

🎯 What it does: A unified, promptable vision foundation model named TAP was constructed, capable of simultaneously performing segmentation, identification, and generating descriptions for any region.

Toward Open Vocabulary Aerial Object Detection with CLIP-Activated Student-Teacher Learning

Yan Li, Wenxian Yu (Tongji University)

CodeObject DetectionKnowledge DistillationConvolutional Neural NetworkTransformerVision Language ModelContrastive LearningImage

🎯 What it does: Propose CastDet, a student-teacher self-learning framework based on the pre-trained RemoteCLIP model, aiming to achieve open-vocabulary object detection (OVD) from a drone perspective, capable of identifying target categories outside the training set without additional annotated data.

Towards Architecture-Agnostic Untrained Networks Priors for Image Reconstruction with Frequency Regularization

Yilin Liu (University of North Carolina at Chapel Hill), Pew-Thian Yap (University of North Carolina at Chapel Hill)

CodeRestorationConvolutional Neural NetworkBiomedical DataMagnetic Resonance Imaging

🎯 What it does: This paper proposes three frequency regularization methods (bandwidth-limited input, controllable upsampler, and learnable Lipschitz regularization), which enhance the performance of untrained networks (e.g., DIP) in medical image reconstruction by directly adjusting the network's frequency bias, eliminating dependency on specific architectures.

Towards High-Quality 3D Motion Transfer with Realistic Apparel Animation

Rong Wang (Australian National University), HONGDONG LI

CodeGenerationGraph Neural NetworkMesh

🎯 What it does: Propose a data-driven 3D motion transfer method that can animate target stylized characters while generating realistic clothing animations.

Towards Image Ambient Lighting Normalization

Florin-Alexandru Vasluianu (University of WΓΌrzburg), Radu Timofte (University of WΓΌrzburg)

CodeRestorationConvolutional Neural NetworkImageBenchmark

🎯 What it does: This paper proposes and studies the Ambient Lighting Normalization (ALN) task, aiming to recover image details in complex multi-light source and self-shadowed scenes.

Towards Latent Masked Image Modeling for Self-Supervised Visual Representation Learning

Yibing Wei (University of Wisconsin Madison), Pedro Morgado (Carnegie Mellon University)

CodeRepresentation LearningTransformerAuto EncoderContrastive LearningImage

🎯 What it does: Propose and systematically evaluate a framework for Latent Masked Image Modeling (Latent MIM) in the latent space, leveraging reconstruction of latent features to learn unsupervised visual representations.

Towards Model-Agnostic Dataset Condensation by Heterogeneous Models

Jun-Yeong Moon (Kyung Hee University), Gyeong-Moon Park (Kyung Hee University)

CodeData SynthesisKnowledge DistillationData-Centric LearningConvolutional Neural NetworkTransformerImage

🎯 What it does: Propose a model-agnostic dataset compression method called HMDC, which generates general synthetic images by using heterogeneous models collaboratively.

Towards Multi-modal Transformers in Federated Learning

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

CodeFederated LearningRepresentation LearningTransformerMixture of ExpertsImageTextMultimodalityBiomedical Data

🎯 What it does: Propose the FedCola framework, addressing cross-modal and modality gap issues between single-modal and multi-modal clients in federated learning through a multi-modal Transformer.

Towards Multimodal Open-Set Domain Generalization and Adaptation through Self-supervision

Hao Dong (ETH ZΓΌrich), Olga Fink (EPFL)

CodeDomain AdaptationAnomaly DetectionAuto EncoderContrastive LearningVideoMultimodalityAudio

🎯 What it does: Proposed the MOOSA method for Multimodal Open-Set Domain Generalization and Adaptation (MMOSDG/MM-OSDA), which learns cross-modal representations through self-supervised tasks and achieves unknown class detection.

Towards Neuro-Symbolic Video Understanding

Minkyu Choi (University of Texas at Austin), Sandeep Chinchali (University of Texas at Austin)

CodeRetrievalExplainability and InterpretabilityTransformerVision Language ModelVideoText

🎯 What it does: Propose a neuro-symbolic video retrieval framework that integrates visual language models with temporal logic and probabilistic automata to real-time locate complex event scenarios in long videos.

Towards Open-ended Visual Quality Comparison

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

CodeTransformerLarge Language ModelSupervised Fine-TuningVision Language ModelMultimodalityBenchmark

🎯 What it does: Developed the LMM Co-Instruct for open-ended visual quality comparison along with its corresponding training set and benchmark.

Towards Open-Ended Visual Recognition with Large Language Models

Qihang Yu (ByteDance), Liang-Chieh Chen (ByteDance)

CodeClassificationRecognitionTransformerLarge Language ModelSupervised Fine-TuningVision Language ModelImage

🎯 What it does: Proposes the OmniScient Model (OSM), a mask classifier based on large language models, achieving open-vision recognition;

Towards Open-World Object-based Anomaly Detection via Self-Supervised Outlier Synthesis

Brian Kostadinov Shalon Isaac-Medina, Toby P Breckon

CodeData SynthesisAnomaly DetectionFlow-based ModelMultimodality

🎯 What it does: This paper proposes an open-world object detection framework based on self-supervised virtual anomaly synthesis (SSOS) to achieve object-level anomaly detection without class labels.

Towards Real-world Event-guided Low-light Video Enhancement and Deblurring

Taewoo Kim (Korea Advanced Institute of Science and Technology), Kuk-Jin Yoon (Korea Advanced Institute of Science and Technology)

CodeRestorationConvolutional Neural NetworkTransformerMultimodality

🎯 What it does: This paper proposes an end-to-end framework that utilizes an event camera to simultaneously enhance low-light videos and remove motion blur.

Towards Reliable Advertising Image Generation Using Human Feedback

Zhenbang Du (Huazhong University of Science and Technology), Jingping Shao (JD)

CodeGenerationData SynthesisConvolutional Neural NetworkTransformerReinforcement LearningVision Language ModelDiffusion modelImageTextMultimodality

🎯 What it does: Proposed a reliable system for generating advertising images, utilizing a multi-modal RFNet to simulate human review and combining cyclic generation with RFFT-refined diffusion models, significantly improving the proportion of usable images.

Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models

Francesco Croce (EPFL), Matthias Hein (University of TΓΌbingen)

CodeSegmentationAdversarial AttackConvolutional Neural NetworkImage

🎯 What it does: This paper proposes a reliable robustness evaluation and fast training method for semantic segmentation models, including a novel attack loss function, attack ensemble, and adversarial training using a robust ImageNet backbone.

Towards Robust Event-based Networks for Nighttime via Unpaired Day-to-Night Event Translation

Yuhwan Jeong (Korea Advanced Institute of Science and Technology), Kuk-Jin Yoon (Korea Advanced Institute of Science and Technology)

CodeImage TranslationData SynthesisDomain AdaptationConvolutional Neural NetworkDiffusion modelGenerative Adversarial NetworkContrastive LearningTime Series

🎯 What it does: Through unpaired event-to-event translation, daytime event data is converted into nighttime events, helping networks that perform well on daytime data maintain performance at night.

Towards Robust Full Low-bit Quantization of Super Resolution Networks

Denis S. Makhov (Noah's Ark Lab Huawei Technologies), Kirill Solodskikh (Noah's Ark Lab Huawei Technologies)

CodeSuper ResolutionConvolutional Neural NetworkImageOrdinary Differential Equation

🎯 What it does: This paper proposes a full low-bit quantization method for super-resolution networks. The core idea is to first map images to the differential operator (edge, texture) domain, enhance the image using a quantized CNN in this domain, and then revert the result back to the original domain through a regularized partial differential equation (PDE) solver, achieving high-quality super-resolution under full 4-bit quantization.

Towards Stable 3D Object Detection

Jiabao Wang (Nankai University), Qibin Hou (Nankai University)

CodeObject DetectionAutonomous DrivingPoint Cloud

🎯 What it does: This paper proposes a Stability Index (SI) metric to measure the temporal stability of 3D object detectors, and develops a Prediction Consistency Learning (PCL) training strategy based on this, significantly improving the consistency of confidence, position, size, and orientation of detectors across consecutive frames.

Trainable Highly-expressive Activation Functions

Irit Chelly (Ben-Gurion University of the Negev), Oren Freifeld (Ben-Gurion University of the Negev)

CodeClassificationSegmentationGenerationImage

🎯 What it does: This paper proposes a trainable, high-expressive activation function called DiTAC, which achieves significant performance improvements across various tasks.

Training A Small Emotional Vision Language Model for Visual Art Comprehension

Jing Zhang (Hefei University of Technology), Dan Guo (Hefei University of Technology)

CodeClassificationGenerationTransformerLarge Language ModelVision Language ModelContrastive LearningImageTextMultimodality

🎯 What it does: Trained and evaluated a small-scale emotion vision-language model SEVLM for emotion classification and emotion explanation generation in visual artworks.

Training-free Composite Scene Generation for Layout-to-Image Synthesis

Jiaqi Liu (University of Sydney), Chang Xu (University of Sydney)

CodeImage TranslationGenerationData SynthesisDiffusion modelImage

🎯 What it does: Propose an untrained composite scene generation method that utilizes layout information to guide Stable Diffusion for multi-object image synthesis.

Training-free Video Temporal Grounding using Large-scale Pre-trained Models

Minghang Zheng (Peking University), Yang Liu (Peking University)

CodeRetrievalTransformerLarge Language ModelVision Language ModelVideoTextChain-of-Thought

🎯 What it does: Propose a training-free video temporal localization method, which first splits queries into sub-events and infers their order and relationships using a large language model, then performs dynamic and static matching for each sub-event with a vision-language model, ultimately obtaining video segments.

TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection

Matic Fučka (University of Ljubljana), Danijel Skočaj (University of Ljubljana)

CodeAnomaly DetectionConvolutional Neural NetworkDiffusion modelImage

🎯 What it does: Proposed a single-stage surface anomaly detection method called TransFusion based on transparency diffusion, which simultaneously reconstructs normal appearance and localizes anomalies in one iteration process;

TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias

Sanghyun Jo (OGQ), Kyungsu Kim (Massachusetts General Hospital and Harvard Medical School)

CodeKnowledge DistillationTransformerVision Language ModelContrastive LearningImageText

🎯 What it does: Proposes the text-label self-distillation method TTD, which mitigates the single-label bias in the CLIP model and achieves more fair image-text alignment by fine-tuning with only image-text pairs.