{"total":188,"rows":[{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175,"area":null},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561,"area":null},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291,"area":null},{"id":"2203.04838","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","created":"2022-03-09","cited_by_count":231,"area":null},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205,"area":null},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193,"area":null},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182,"area":null},{"id":"2203.07303","title":"All in One: Exploring Unified Video-Language Pre-training","created":"2022-03-14","cited_by_count":171,"area":null},{"id":"2302.03024","title":"AIM: Adapting Image Models for Efficient Video Action Recognition","created":"2023-02-06","cited_by_count":148,"area":null},{"id":"2303.01480","title":"Delivering Arbitrary-Modal Semantic Segmentation","created":"2023-03-02","cited_by_count":117,"area":null},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115,"area":null},{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104,"area":null},{"id":"2206.08356","title":"OmniMAE: Single Model Masked Pretraining on Images and Videos","created":"2022-06-16","cited_by_count":99,"area":null},{"id":"2207.07078","title":"Towards Grand Unification of Object Tracking","created":"2022-07-14","cited_by_count":93,"area":null},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84,"area":null},{"id":"2306.02050","title":"Provable Dynamic Fusion for Low-Quality Multimodal Data","created":"2023-06-03","cited_by_count":82,"area":null},{"id":"2212.07983","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","created":"2022-12-15","cited_by_count":72,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2404.08351","title":"OmniSat: Self-Supervised Modality Fusion for Earth Observation","created":"2024-04-12","cited_by_count":63,"area":null},{"id":"2309.09668","title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","created":"2023-09-18","cited_by_count":60,"area":null},{"id":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55,"area":null},{"id":"2210.03265","title":"Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks","created":"2022-10-07","cited_by_count":52,"area":null},{"id":"2301.02074","title":"Test of Time: Instilling Video-Language Models with a Sense of Time","created":"2023-01-05","cited_by_count":51,"area":null},{"id":"2312.14556","title":"CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities","created":"2023-12-22","cited_by_count":51,"area":null},{"id":"2212.03229","title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning","created":"2022-12-06","cited_by_count":49,"area":null},{"id":"2212.05922","title":"Audiovisual Masked Autoencoders","created":"2022-12-09","cited_by_count":49,"area":null},{"id":"2404.18947","title":"Multimodal Fusion on Low-quality Data: A Comprehensive Survey","created":"2024-04-27","cited_by_count":49,"area":null},{"id":"2502.12191","title":"AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors","created":"2025-02-15","cited_by_count":48,"area":null},{"id":"2302.00646","title":"Epic-Sounds: A Large-scale Dataset of Actions That Sound","created":"2023-02-01","cited_by_count":47,"area":null},{"id":"2407.00224","title":"Multimodal Prototyping for cancer survival prediction","created":"2024-06-28","cited_by_count":47,"area":null},{"id":"2311.05709","title":"OmniVec: Learning robust representations with cross modal sharing","created":"2023-11-07","cited_by_count":44,"area":null},{"id":"2406.01210","title":"GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer","created":"2024-06-03","cited_by_count":44,"area":null},{"id":"2406.18070","title":"EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation","created":"2024-06-26","cited_by_count":44,"area":null},{"id":"2210.12649","title":"Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation","created":"2022-10-23","cited_by_count":41,"area":null},{"id":"2303.09857","title":"Dual-path Adaptation from Image to Video Transformers","created":"2023-03-17","cited_by_count":41,"area":null},{"id":"2207.07036","title":"u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality","created":"2022-07-14","cited_by_count":39,"area":null},{"id":"2308.07893","title":"Memory-and-Anticipation Transformer for Online Action Understanding","created":"2023-08-15","cited_by_count":39,"area":null},{"id":"2408.01343","title":"StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation","created":"2024-08-02","cited_by_count":39,"area":null},{"id":"2207.10430","title":"The Neural Race Reduction: Dynamics of Abstraction in Gated Networks","created":"2022-07-21","cited_by_count":37,"area":null},{"id":"2309.05300","title":"Decoupling Common and Unique Representations for Multimodal Self-supervised Learning","created":"2023-09-11","cited_by_count":36,"area":null},{"id":"2307.08763","title":"Video-Mined Task Graphs for Keystep Recognition in Instructional Videos","created":"2023-07-17","cited_by_count":35,"area":null},{"id":"2301.02217","title":"EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding","created":"2023-01-05","cited_by_count":32,"area":null},{"id":"2301.01380","title":"Ego-Only: Egocentric Action Detection without Exocentric Transferring","created":"2023-01-03","cited_by_count":31,"area":null},{"id":"2504.04701","title":"DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation","created":"2025-04-07","cited_by_count":31,"area":null},{"id":"2311.16081","title":"ViT-Lens: Towards Omni-modal Representations","created":"2023-11-27","cited_by_count":29,"area":null},{"id":"2305.15701","title":"Action Sensitivity Learning for Temporal Action Localization","created":"2023-05-25","cited_by_count":28,"area":null},{"id":"2205.06126","title":"One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code","created":"2022-05-12","cited_by_count":26,"area":null},{"id":"2209.05700","title":"Vision Transformers for Action Recognition: A Survey","created":"2022-09-13","cited_by_count":25,"area":null},{"id":"2312.00360","title":"Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning","created":"2023-12-01","cited_by_count":25,"area":null},{"id":"2401.02416","title":"ODIN: A Single Model for 2D and 3D Segmentation","created":"2024-01-04","cited_by_count":25,"area":null},{"id":"2311.00180","title":"Object-centric Video Representation for Long-term Action Anticipation","created":"2023-10-31","cited_by_count":24,"area":null},{"id":"2304.03959","title":"StillFast: An End-to-End Approach for Short-Term Object Interaction Anticipation","created":"2023-04-08","cited_by_count":23,"area":null},{"id":"2206.09852","title":"M&M Mix: A Multimodal Multiview Transformer Ensemble","created":"2022-06-20","cited_by_count":20,"area":null},{"id":"2309.16669","title":"Training a Large Video Model on a Single Machine in a Day","created":"2023-09-28","cited_by_count":20,"area":null},{"id":"2207.00383","title":"ReLER@ZJU-Alibaba Submission to the Ego4D Natural Language Queries Challenge 2022","created":"2022-07-01","cited_by_count":19,"area":null},{"id":"2212.06301","title":"Egocentric Video Task Translation","created":"2022-12-13","cited_by_count":19,"area":null},{"id":"2306.15850","title":"SpotEM: Efficient Video Search for Episodic Memory","created":"2023-06-28","cited_by_count":17,"area":null},{"id":"2309.14065","title":"AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic Segmentation","created":"2023-09-25","cited_by_count":17,"area":null},{"id":"2312.02638","title":"Synchronization is All You Need: Exocentric-to-Egocentric Transfer for Temporal Action Segmentation with Unlabeled Synchronized Video Pairs","created":"2023-12-05","cited_by_count":17,"area":null},{"id":"2210.08457","title":"Scratching Visual Transformer's Back with Uniform Attention","created":"2022-10-16","cited_by_count":16,"area":null},{"id":"2404.05559","title":"TIM: A Time Interval Machine for Audio-Visual Action Recognition","created":"2024-04-08","cited_by_count":15,"area":null},{"id":"2411.02256","title":"Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs","created":"2024-11-04","cited_by_count":15,"area":null},{"id":"2303.12001","title":"ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders","created":"2023-03-21","cited_by_count":14,"area":null},{"id":"2311.05770","title":"PolyMaX: General Dense Prediction with Mask Transformer","created":"2023-11-09","cited_by_count":14,"area":null},{"id":"2403.19638","title":"Siamese Vision Transformers are Scalable Audio-visual Learners","created":"2024-03-28","cited_by_count":14,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2507.13364","title":"OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","created":"2025-07-06","cited_by_count":14,"area":null},{"id":"2303.06457","title":"Active Visual Exploration Based on Attention-Map Entropy","created":"2023-03-11","cited_by_count":13,"area":null},{"id":"2401.11204","title":"Towards Category Unification of 3D Single Object Tracking on Point Clouds","created":"2024-01-20","cited_by_count":13,"area":null},{"id":"2210.00843","title":"Early or Late Fusion Matters: Efficient RGB-D Fusion in Vision Transformers for 3D Object Recognition","created":"2022-10-03","cited_by_count":12,"area":null},{"id":"2306.12795","title":"Learning Unseen Modality Interaction","created":"2023-06-22","cited_by_count":12,"area":null},{"id":"2311.18825","title":"CAST: Cross-Attention in Space and Time for Video Action Recognition","created":"2023-11-30","cited_by_count":12,"area":null},{"id":"2312.10144","title":"Data-Efficient Multimodal Fusion on a Single GPU","created":"2023-12-15","cited_by_count":11,"area":null},{"id":"2401.16923","title":"Fourier Prompt Tuning for Modality-Incomplete Scene Segmentation","created":"2024-01-30","cited_by_count":11,"area":null},{"id":"2209.09070","title":"SOCRATES: A Stereo Camera Trap for Monitoring of Biodiversity","created":"2022-09-19","cited_by_count":10,"area":null},{"id":"2301.00362","title":"Goal-Guided Transformer-Enabled Reinforcement Learning for Efficient Autonomous Navigation","created":"2023-01-01","cited_by_count":10,"area":null},{"id":"2303.17376","title":"A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision","created":"2023-03-30","cited_by_count":10,"area":null},{"id":"2309.15762","title":"Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedback","created":"2023-09-27","cited_by_count":10,"area":null},{"id":"2404.03527","title":"HAPNet: Toward Superior RGB-Thermal Scene Parsing via Hybrid, Asymmetric, and Progressive Heterogeneous Feature Fusion","created":"2024-04-04","cited_by_count":10,"area":null},{"id":"2412.18277","title":"Towards Modality Generalization: A Benchmark and Prospective Analysis","created":"2024-12-24","cited_by_count":10,"area":null},{"id":"2306.10354","title":"LLMVA-GEBC: Large Language Model with Video Adapter for Generic Event Boundary Captioning","created":"2023-06-17","cited_by_count":9,"area":null},{"id":"2403.03037","title":"A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives","created":"2024-03-05","cited_by_count":9,"area":null},{"id":"2406.13123","title":"ViLCo-Bench: VIdeo Language COntinual learning Benchmark","created":"2024-06-19","cited_by_count":9,"area":null},{"id":"2412.00932","title":"FIction: 4D Future Interaction Prediction from Video","created":"2024-12-01","cited_by_count":9,"area":null},{"id":"2502.20249","title":"Enhancing 3D Gaze Estimation in the Wild using Weak Supervision with Gaze Following Labels","created":"2025-02-27","cited_by_count":9,"area":null},{"id":"2504.13101","title":"Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research","created":"2025-04-17","cited_by_count":9,"area":null},{"id":"2209.07026","title":"Can We Solve 3D Vision Tasks Starting from A 2D Vision Transformer?","created":"2022-09-15","cited_by_count":8,"area":null},{"id":"2302.06148","title":"CoMAE: Single Model Hybrid Pre-training on Small-Scale RGB-D Datasets","created":"2023-02-13","cited_by_count":8,"area":null},{"id":"2409.06535","title":"PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation","created":"2024-09-10","cited_by_count":8,"area":null},{"id":"2306.05242","title":"Efficient Multi-Task Scene Analysis with RGB-D Transformers","created":"2023-06-08","cited_by_count":7,"area":null},{"id":"2306.09172","title":"Action Sensitivity Learning for the Ego4D Episodic Memory Challenge 2023","created":"2023-06-15","cited_by_count":7,"area":null},{"id":"2312.00826","title":"DEVIAS: Learning Disentangled Video Representations of Action and Scene","created":"2023-11-30","cited_by_count":7,"area":null},{"id":"2401.01823","title":"Detours for Navigating Instructional Videos","created":"2024-01-03","cited_by_count":7,"area":null},{"id":"2407.08148","title":"SCPNet: Unsupervised Cross-modal Homography Estimation via Intra-modal Self-supervised Learning","created":"2024-07-11","cited_by_count":7,"area":null},{"id":"2505.12911","title":"HiERO: understanding the hierarchy of human behavior enhances reasoning on egocentric videos","created":"2025-05-19","cited_by_count":7,"area":null},{"id":"2208.12259","title":"Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud Understanding","created":"2022-08-25","cited_by_count":6,"area":null},{"id":"2211.08704","title":"A Simple Transformer-Based Model for Ego4D Natural Language Queries Challenge","created":"2022-11-16","cited_by_count":6,"area":null}],"next_cursor":"100"}