{"total":102,"rows":[{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386,"area":"mllm"},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232,"area":null},{"id":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226,"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":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193,"area":null},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169,"area":null},{"id":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140,"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":"2412.14058","title":"What Matters in Building Vision-Language-Action Models for Generalist Robots","created":"2024-12-18","cited_by_count":89,"area":"mllm"},{"id":"2201.10990","title":"Learning To Recognize Procedural Activities with Distant Supervision","created":"2022-01-26","cited_by_count":85,"area":null},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"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":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"id":"2209.06430","title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","created":"2022-09-14","cited_by_count":74,"area":null},{"id":"2206.07160","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","created":"2022-06-14","cited_by_count":73,"area":null},{"id":"2212.04979","title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","created":"2022-12-09","cited_by_count":70,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2308.11062","title":"UnLoc: A Unified Framework for Video Localization Tasks","created":"2023-08-21","cited_by_count":66,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2407.03104","title":"KeyVideoLLM: Towards Large-scale Video Keyframe Selection","created":"2024-07-03","cited_by_count":54,"area":null},{"id":"2303.18230","title":"Procedure-Aware Pretraining for Instructional Video Understanding","created":"2023-03-31","cited_by_count":48,"area":null},{"id":"2301.00746","title":"NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory","created":"2023-01-02","cited_by_count":46,"area":null},{"id":"2306.07520","title":"Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions","created":"2023-06-13","cited_by_count":46,"area":null},{"id":"2207.10362","title":"LocVTP: Video-Text Pre-training for Temporal Localization","created":"2022-07-21","cited_by_count":44,"area":null},{"id":"2203.06667","title":"Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video","created":"2022-03-13","cited_by_count":43,"area":null},{"id":"2207.07885","title":"Clover: Towards A Unified Video-Language Alignment and Fusion Model","created":"2022-07-16","cited_by_count":41,"area":null},{"id":"2311.17618","title":"ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Model","created":"2023-11-29","cited_by_count":39,"area":"mllm"},{"id":"2201.08071","title":"Temporal Sentence Grounding in Videos: A Survey and Future Directions","created":"2022-01-20","cited_by_count":37,"area":null},{"id":"2406.05615","title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","created":"2024-06-09","cited_by_count":37,"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":"2308.07648","title":"Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval","created":"2023-08-15","cited_by_count":35,"area":null},{"id":"2204.12408","title":"MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval","created":"2022-04-26","cited_by_count":29,"area":null},{"id":"2303.12423","title":"Text with Knowledge Graph Augmented Transformer for Video Captioning","created":"2023-03-22","cited_by_count":28,"area":null},{"id":"2303.14655","title":"GOAL: A Challenging Knowledge-grounded Video Captioning Benchmark for Real-time Soccer Commentary Generation","created":"2023-03-26","cited_by_count":28,"area":null},{"id":"2109.09920","title":"Survey: Transformer based Video-Language Pre-training","created":"2021-09-21","cited_by_count":27,"area":null},{"id":"2305.04701","title":"Differentially Private Attention Computation","created":"2023-05-08","cited_by_count":25,"area":null},{"id":"2206.05314","title":"Large-Scale Retrieval for Reinforcement Learning","created":"2022-06-10","cited_by_count":24,"area":"offlinerl"},{"id":"2207.02159","title":"Robustness Analysis of Video-Language Models Against Visual and Language Perturbations","created":"2022-07-05","cited_by_count":23,"area":null},{"id":"2308.08414","title":"Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer","created":"2023-08-16","cited_by_count":22,"area":null},{"id":"2408.13233","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","created":"2024-08-23","cited_by_count":22,"area":null},{"id":"2203.08013","title":"End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding","created":"2022-03-15","cited_by_count":19,"area":null},{"id":"2303.06591","title":"Accommodating Audio Modality in CLIP for Multimodal Processing","created":"2023-03-12","cited_by_count":18,"area":"mllm"},{"id":"2306.15850","title":"SpotEM: Efficient Video Search for Episodic Memory","created":"2023-06-28","cited_by_count":17,"area":null},{"id":"2312.06729","title":"RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos","created":"2023-12-11","cited_by_count":15,"area":null},{"id":"2203.03014","title":"Learnable Irrelevant Modality Dropout for Multimodal Action Recognition on Modality-Specific Annotated Videos","created":"2022-03-06","cited_by_count":14,"area":null},{"id":"2502.04981","title":"AutoOcc: Automatic Open-Ended Semantic Occupancy Annotation via Vision-Language Guided Gaussian Splatting","created":"2025-02-07","cited_by_count":14,"area":"mllm"},{"id":"2210.04829","title":"Hierarchical3D Adapters for Long Video-to-text Summarization","created":"2022-10-10","cited_by_count":12,"area":null},{"id":"2603.07135","title":"The Model Knows Which Tokens Matter: Automatic Token Selection via Noise Gating","created":"2026-03-07","cited_by_count":11,"area":"mllm"},{"id":"2210.05234","title":"It Takes Two: Masked Appearance-Motion Modeling for Self-supervised Video Transformer Pre-training","created":"2022-10-11","cited_by_count":10,"area":null},{"id":"2303.12370","title":"Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos","created":"2023-03-22","cited_by_count":10,"area":null},{"id":"2508.09486","title":"Video-EM: Event-Centric Episodic Memory for Long-Form Video Understanding","created":"2025-08-13","cited_by_count":10,"area":null},{"id":"2211.02077","title":"Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization","created":"2022-11-03","cited_by_count":9,"area":null},{"id":"2505.19139","title":"The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework","created":"2025-05-25","cited_by_count":9,"area":null},{"id":"2303.06378","title":"Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos","created":"2023-03-11","cited_by_count":8,"area":null},{"id":"2407.03788","title":"MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning","created":"2024-07-04","cited_by_count":8,"area":null},{"id":"2301.01953","title":"Learning Trajectory-Word Alignments for Video-Language Tasks","created":"2023-01-05","cited_by_count":7,"area":null},{"id":"2302.09473","title":"Video-Text Retrieval by Supervised Sparse Multi-Grained Learning","created":"2023-02-19","cited_by_count":7,"area":null},{"id":"2408.12885","title":"T3M: Text Guided 3D Human Motion Synthesis from Speech","created":"2024-08-23","cited_by_count":6,"area":null},{"id":"2302.09736","title":"STOA-VLP: Spatial-Temporal Modeling of Object and Action for Video-Language Pre-training","created":"2023-02-20","cited_by_count":5,"area":null},{"id":"2310.13859","title":"Not all Fake News is Written: A Dataset and Analysis of Misleading Video Headlines","created":"2023-10-20","cited_by_count":5,"area":null},{"id":"2401.17797","title":"M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval","created":"2024-01-31","cited_by_count":5,"area":null},{"id":"2405.17790","title":"Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-identification","created":"2024-05-28","cited_by_count":5,"area":null},{"id":"2603.20194","title":"MME-CoF-Pro: Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hints","created":"2026-03-20","cited_by_count":5,"area":"lr"},{"id":"2402.09055","title":"Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection","created":"2024-02-14","cited_by_count":4,"area":null},{"id":"2402.13566","title":"Event-aware Video Corpus Moment Retrieval","created":"2024-02-21","cited_by_count":4,"area":null},{"id":"2410.17149","title":"Are Visual-Language Models Effective in Action Recognition? A Comparative Study","created":"2024-10-22","cited_by_count":4,"area":"mllm"},{"id":"2503.10665","title":"Small Vision-Language Models: A Survey on Compact Architectures and Techniques","created":"2025-03-09","cited_by_count":4,"area":"mllm"},{"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":"2212.01638","title":"VLG: General Video Recognition with Web Textual Knowledge","created":"2022-12-03","cited_by_count":3,"area":null},{"id":"2401.07510","title":"Developing ChatGPT for Biology and Medicine: A Complete Review of Biomedical Question Answering","created":"2024-01-15","cited_by_count":3,"area":null},{"id":"2404.05083","title":"DREAM: Improving Video-Text Retrieval Through Relevance-Based Augmentation Using Large Foundation Models","created":"2024-04-07","cited_by_count":3,"area":null},{"id":"2408.11432","title":"T2VIndexer: A Generative Video Indexer for Efficient Text-Video Retrieval","created":"2024-08-21","cited_by_count":3,"area":null},{"id":"2410.01144","title":"Uncertainty-Guided Enhancement on Driving Perception System via Foundation Models","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2506.22967","title":"ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence Alignment","created":"2025-06-28","cited_by_count":3,"area":null},{"id":"2310.05511","title":"Proposal-based Temporal Action Localization with Point-level Supervision","created":"2023-10-09","cited_by_count":2,"area":null},{"id":"2406.03439","title":"Text-to-Events: Synthetic Event Camera Streams from Conditional Text Input","created":"2024-06-05","cited_by_count":2,"area":"diffusion"},{"id":"2504.05700","title":"Pose-Aware Weakly-Supervised Action Segmentation","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2111.01677","title":"Top1 Solution of QQ Browser 2021 Ai Algorithm Competition Track 1 : Multimodal Video Similarity","created":"2021-10-30","cited_by_count":1,"area":null},{"id":"2210.05038","title":"Fighting FIRe with FIRE: Assessing the Validity of Text-to-Video Retrieval Benchmarks","created":"2022-10-10","cited_by_count":1,"area":null},{"id":"2211.07210","title":"Grafting Pre-trained Models for Multimodal Headline Generation","created":"2022-11-14","cited_by_count":1,"area":null},{"id":"2303.16341","title":"Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding","created":"2023-03-28","cited_by_count":1,"area":null},{"id":"2305.04824","title":"Learning Summary-Worthy Visual Representation for Abstractive Summarization in Video","created":"2023-05-08","cited_by_count":1,"area":null},{"id":"2307.10567","title":"No-frills Temporal Video Grounding: Multi-Scale Neighboring Attention and Zoom-in Boundary Detection","created":"2023-07-20","cited_by_count":1,"area":null},{"id":"2309.00696","title":"AAN: Attributes-Aware Network for Temporal Action Detection","created":"2023-09-01","cited_by_count":1,"area":null},{"id":"2310.17189","title":"Exploring Iterative Refinement with Diffusion Models for Video Grounding","created":"2023-10-26","cited_by_count":1,"area":"diffusion"},{"id":"2312.00115","title":"A Video is Worth 10,000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval","created":"2023-11-30","cited_by_count":1,"area":null},{"id":"2401.17773","title":"SNP-S3: Shared Network Pre-training and Significant Semantic Strengthening for Various Video-Text Tasks","created":"2024-01-31","cited_by_count":1,"area":null},{"id":"2408.15714","title":"Pixels to Prose: Understanding the art of Image Captioning","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2410.07405","title":"Exploring Efficient Foundational Multi-modal Models for Video Summarization","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2506.12936","title":"CliniDial: A Naturally Occurring Multimodal Dialogue Dataset for Team Reflection in Action During Clinical Operation","created":"2025-06-15","cited_by_count":1,"area":null},{"id":"2511.15379","title":"Zero-Shot Open-Vocabulary Human Motion Grounding with Test-Time Training","created":"2025-11-19","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":"2211.03314","title":"CLOP: Video-and-Language Pre-Training with Knowledge Regularizations","created":"2022-11-07","cited_by_count":0,"area":null},{"id":"2311.17267","title":"E-ViLM: Efficient Video-Language Model via Masked Video Modeling with Semantic Vector-Quantized Tokenizer","created":"2023-11-28","cited_by_count":0,"area":null},{"id":"2405.14142","title":"Imagery as Inquiry: Exploring A Multimodal Dataset for Conversational Recommendation","created":"2024-05-23","cited_by_count":0,"area":null},{"id":"2406.07091","title":"AutoTVG: A New Vision-language Pre-training Paradigm for Temporal Video Grounding","created":"2024-06-11","cited_by_count":0,"area":"mllm"},{"id":"2507.23178","title":"AutoBridge: Automating Smart Device Integration with Centralized Platform","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2606.21607","title":"T-MOR: Learning Motion-Aware Skeleton Representations for Human Action Recognition","created":"2026-06-19","cited_by_count":0,"area":"mllm"}],"next_cursor":"100"}