{"total":94,"rows":[{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232,"area":null},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205,"area":null},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130,"area":null},{"id":"2104.10054","title":"T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval","created":"2021-04-20","cited_by_count":103,"area":null},{"id":"2103.16553","title":"Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers","created":"2021-03-30","cited_by_count":93,"area":null},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"area":null},{"id":"2104.08271","title":"TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval","created":"2021-04-16","cited_by_count":81,"area":null},{"id":"2201.04850","title":"Bridging Video-text Retrieval with Multiple Choice Questions","created":"2022-01-13","cited_by_count":79,"area":null},{"id":"2103.10699","title":"MDMMT: Multidomain Multimodal Transformer for Video Retrieval","created":"2021-03-19","cited_by_count":78,"area":null},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2112.12777","title":"Cross Modal Retrieval with Querybank Normalisation","created":"2021-12-23","cited_by_count":72,"area":null},{"id":"2104.09496","title":"Temporal Query Networks for Fine-grained Video Understanding","created":"2021-04-19","cited_by_count":68,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2107.02423","title":"Improving Text-to-Image Synthesis Using Contrastive Learning","created":"2021-07-06","cited_by_count":62,"area":null},{"id":"2203.13049","title":"Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning","created":"2022-03-24","cited_by_count":59,"area":null},{"id":"2103.10095","title":"On Semantic Similarity in Video Retrieval","created":"2021-03-18","cited_by_count":46,"area":null},{"id":"2103.05284","title":"Open-book Video Captioning with Retrieve-Copy-Generate Network","created":"2021-03-09","cited_by_count":43,"area":null},{"id":"2111.01024","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","created":"2021-11-01","cited_by_count":41,"area":null},{"id":"2203.11637","title":"Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos","created":"2022-03-22","cited_by_count":39,"area":null},{"id":"2204.02874","title":"ECLIPSE: Efficient Long-range Video Retrieval using Sight and Sound","created":"2022-04-06","cited_by_count":39,"area":null},{"id":"2304.03391","title":"Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval","created":"2023-04-06","cited_by_count":36,"area":null},{"id":"2201.09168","title":"Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval","created":"2022-01-23","cited_by_count":34,"area":null},{"id":"2109.10016","title":"CONQUER: Contextual Query-aware Ranking for Video Corpus Moment Retrieval","created":"2021-09-21","cited_by_count":33,"area":null},{"id":"2305.12218","title":"Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment","created":"2023-05-20","cited_by_count":32,"area":null},{"id":"2107.12059","title":"HANet: Hierarchical Alignment Networks for Video-Text Retrieval","created":"2021-07-26","cited_by_count":31,"area":null},{"id":"2307.12545","title":"Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Model","created":"2023-07-24","cited_by_count":25,"area":null},{"id":"2101.11530","title":"Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition","created":"2021-01-27","cited_by_count":24,"area":null},{"id":"2203.16784","title":"Video-Text Representation Learning via Differentiable Weak Temporal Alignment","created":"2022-03-31","cited_by_count":24,"area":null},{"id":"2308.03950","title":"Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization","created":"2023-08-07","cited_by_count":24,"area":null},{"id":"2406.19874","title":"Detecting Subtle Differences between Human and Model Languages Using Spectrum of Relative Likelihood","created":"2024-06-28","cited_by_count":24,"area":null},{"id":"2112.01832","title":"Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval","created":"2021-12-03","cited_by_count":23,"area":null},{"id":"2201.02495","title":"Sign Language Video Retrieval with Free-Form Textual Queries","created":"2022-01-07","cited_by_count":23,"area":null},{"id":"2406.13327","title":"Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition","created":"2024-06-19","cited_by_count":23,"area":null},{"id":"2301.09017","title":"Transfer Knowledge from Natural Language to Electrocardiography: Can We Detect Cardiovascular Disease Through Language Models?","created":"2023-01-21","cited_by_count":21,"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":"2301.09071","title":"Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding","created":"2023-01-22","cited_by_count":19,"area":null},{"id":"2404.07487","title":"Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition","created":"2024-04-11","cited_by_count":19,"area":null},{"id":"2407.13460","title":"SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders","created":"2024-07-18","cited_by_count":19,"area":null},{"id":"2302.12552","title":"Deep Learning for Video-Text Retrieval: a Review","created":"2023-02-24","cited_by_count":15,"area":null},{"id":"2208.02080","title":"A Feature-space Multimodal Data Augmentation Technique for Text-video Retrieval","created":"2022-08-03","cited_by_count":13,"area":null},{"id":"2411.11288","title":"Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition","created":"2024-11-18","cited_by_count":13,"area":null},{"id":"2405.17719","title":"Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?","created":"2024-05-28","cited_by_count":11,"area":null},{"id":"2306.08789","title":"Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training","created":"2023-06-15","cited_by_count":10,"area":null},{"id":"2309.11082","title":"Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning","created":"2023-09-20","cited_by_count":10,"area":null},{"id":"2309.09592","title":"Multi-Semantic Fusion Model for Generalized Zero-Shot Skeleton-Based Action Recognition","created":"2023-09-18","cited_by_count":9,"area":null},{"id":"2409.14336","title":"Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment","created":"2024-09-22","cited_by_count":9,"area":null},{"id":"2110.15609","title":"BiC-Net: Learning Efficient Spatio-Temporal Relation for Text-Video Retrieval","created":"2021-10-29","cited_by_count":8,"area":null},{"id":"2111.04823","title":"Cascaded Multilingual Audio-Visual Learning from Videos","created":"2021-11-08","cited_by_count":8,"area":null},{"id":"2202.03384","title":"Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval","created":"2022-02-07","cited_by_count":8,"area":null},{"id":"2212.11790","title":"Normalized Contrastive Learning for Text-Video Retrieval","created":"2022-11-30","cited_by_count":8,"area":null},{"id":"2303.15086","title":"Learning Action Changes by Measuring Verb-Adverb Textual Relationships","created":"2023-03-27","cited_by_count":8,"area":null},{"id":"2208.12510","title":"PRVR: Partially Relevant Video Retrieval","created":"2022-08-26","cited_by_count":7,"area":null},{"id":"2406.00639","title":"An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition","created":"2024-06-02","cited_by_count":7,"area":null},{"id":"2110.12812","title":"Domain Adaptation in Multi-View Embedding for Cross-Modal Video Retrieval","created":"2021-10-25","cited_by_count":6,"area":null},{"id":"2203.08688","title":"Learning video retrieval models with relevance-aware online mining","created":"2022-03-16","cited_by_count":6,"area":null},{"id":"2204.03734","title":"MHMS: Multimodal Hierarchical Multimedia Summarization","created":"2022-04-07","cited_by_count":6,"area":null},{"id":"2204.13001","title":"Relevance-based Margin for Contrastively-trained Video Retrieval Models","created":"2022-04-27","cited_by_count":6,"area":null},{"id":"2210.04722","title":"Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment","created":"2022-10-10","cited_by_count":6,"area":null},{"id":"2303.05093","title":"Improving Video Retrieval by Adaptive Margin","created":"2023-03-09","cited_by_count":6,"area":null},{"id":"2404.14066","title":"SHE-Net: Syntax-Hierarchy-Enhanced Text-Video Retrieval","created":"2024-04-22","cited_by_count":6,"area":null},{"id":"2506.22179","title":"Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition","created":"2025-06-27","cited_by_count":6,"area":null},{"id":"2103.14785","title":"A Comprehensive Review of the Video-to-Text Problem","created":"2021-03-27","cited_by_count":5,"area":null},{"id":"2206.14381","title":"Exploiting Semantic Role Contextualized Video Features for Multi-Instance Text-Video Retrieval EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022","created":"2022-06-29","cited_by_count":5,"area":null},{"id":"2407.16394","title":"SEDS: Semantically Enhanced Dual-Stream Encoder for Sign Language Retrieval","created":"2024-07-23","cited_by_count":5,"area":null},{"id":"2108.10059","title":"ZS-SLR: Zero-Shot Sign Language Recognition from RGB-D Videos","created":"2021-08-23","cited_by_count":4,"area":null},{"id":"2507.00566","title":"Zero-Shot Skeleton-Based Action Recognition With Prototype-Guided Feature Alignment","created":"2025-07-01","cited_by_count":4,"area":null},{"id":"2210.04341","title":"ConTra: (Con)text (Tra)nsformer for Cross-Modal Video Retrieval","created":"2022-10-09","cited_by_count":3,"area":null},{"id":"2506.14356","title":"EVA02-AT: Egocentric Video-Language Understanding with Spatial-Temporal Rotary Positional Embeddings and Symmetric Optimization","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2511.09388","title":"Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition","created":"2025-11-12","cited_by_count":3,"area":null},{"id":"2512.11458","title":"Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation","created":"2025-12-12","cited_by_count":3,"area":null},{"id":"2603.29692","title":"SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognition","created":"2026-03-31","cited_by_count":3,"area":null},{"id":"2105.03641","title":"Diversifying Neural Text Generation with Part-of-Speech Guided Softmax and Sampling","created":"2021-05-08","cited_by_count":2,"area":null},{"id":"2207.01334","title":"Egocentric Video-Language Pretraining @ EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2406.12256","title":"Symmetric Multi-Similarity Loss for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2024","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2102.13360","title":"A Universal Model for Cross Modality Mapping by Relational Reasoning","created":"2021-02-26","cited_by_count":1,"area":null},{"id":"2206.10903","title":"UniUD-FBK-UB-UniBZ Submission to the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2022","created":"2022-06-22","cited_by_count":1,"area":null},{"id":"2306.04345","title":"An Overview of Challenges in Egocentric Text-Video Retrieval","created":"2023-06-07","cited_by_count":1,"area":null},{"id":"2309.15086","title":"Video-adverb retrieval with compositional adverb-action embeddings","created":"2023-09-26","cited_by_count":1,"area":null},{"id":"2402.02335","title":"Video Editing for Video Retrieval","created":"2024-02-04","cited_by_count":1,"area":null},{"id":"2410.12407","title":"Beyond Coarse-Grained Matching in Video-Text Retrieval","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2505.23952","title":"Leveraging Auxiliary Information in Text-to-Video Retrieval: A Review","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2512.11941","title":"DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognition","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2603.08202","title":"MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2604.02222","title":"SCALE: Semantic- and Confidence-Aware Conditional Variational Autoencoder for Zero-shot Skeleton-based Action Recognition","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2203.12344","title":"How Do You Do It? Fine-Grained Action Understanding with Pseudo-Adverbs","created":"2022-03-23","cited_by_count":0,"area":null},{"id":"2306.15445","title":"UniUD Submission to the EPIC-Kitchens-100 Multi-Instance Retrieval Challenge 2023","created":"2023-06-27","cited_by_count":0,"area":null},{"id":"2508.14812","title":"Repeating Words for Video-Language Retrieval with Coarse-to-Fine Objectives","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2509.15642","title":"UNIV: Unified Foundation Model for Infrared and Visible Modalities","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2512.13511","title":"Adapting MLLMs for Nuanced Video Retrieval","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2604.17013","title":"Toward Universal Skeleton-Based Action Recognition across Heterogeneous Skeletons and Open Vocabularies","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.11497","title":"PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognition","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.22697","title":"Cross-Domain Human Action Recognition from Multiview Motion and Textual Descriptions","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2607.19889","title":"Latent-Action-Guided Video-Language Feature Learning for Surgical Instrument-Tissue Interaction Recognition","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.02236","title":"GenPrior: Unleashing Text-to-Motion Generative Priors for Zero-Shot Skeleton-based Action Recognition","created":"2026-08-03","cited_by_count":0,"area":null}],"next_cursor":null}