{"total":149,"rows":[{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322,"area":"mllm"},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393,"area":null},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328,"area":"ssm"},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263,"area":"mllm"},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229,"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":"2303.16058","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","created":"2023-03-28","cited_by_count":199,"area":null},{"id":"2205.12005","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","created":"2022-05-24","cited_by_count":187,"area":null},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"area":"mllm"},{"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":"2205.06743","title":"A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities","created":"2022-05-13","cited_by_count":163,"area":null},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154,"area":null},{"id":"2209.07526","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","created":"2022-09-15","cited_by_count":143,"area":null},{"id":"2206.03428","title":"Revealing Single Frame Bias for Video-and-Language Learning","created":"2022-06-07","cited_by_count":133,"area":null},{"id":"2205.10747","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","created":"2022-05-22","cited_by_count":117,"area":null},{"id":"2301.09121","title":"Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision","created":"2023-01-22","cited_by_count":99,"area":null},{"id":"2212.04145","title":"Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation","created":"2022-12-08","cited_by_count":98,"area":null},{"id":"2212.05051","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","created":"2022-12-09","cited_by_count":87,"area":null},{"id":"2312.06720","title":"Audio-Visual LLM for Video Understanding","created":"2023-12-11","cited_by_count":77,"area":"mllm"},{"id":"2209.01540","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","created":"2022-09-04","cited_by_count":74,"area":null},{"id":"2212.14546","title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","created":"2022-12-30","cited_by_count":72,"area":null},{"id":"2303.11327","title":"3D Concept Learning and Reasoning from Multi-View Images","created":"2023-03-20","cited_by_count":60,"area":"lr"},{"id":"2305.10724","title":"Segment Any Anomaly without Training via Hybrid Prompt Regularization","created":"2023-05-18","cited_by_count":60,"area":null},{"id":"2209.09019","title":"LAVIS: A Library for Language-Vision Intelligence","created":"2022-09-15","cited_by_count":55,"area":null},{"id":"2311.17404","title":"VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models","created":"2023-11-29","cited_by_count":55,"area":null},{"id":"2208.08340","title":"Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model","created":"2022-08-17","cited_by_count":52,"area":"mllm"},{"id":"2308.14746","title":"CoVR-2: Automatic Data Construction for Composed Video Retrieval","created":"2023-08-28","cited_by_count":52,"area":null},{"id":"2310.19060","title":"TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding","created":"2023-10-29","cited_by_count":49,"area":null},{"id":"2303.18230","title":"Procedure-Aware Pretraining for Instructional Video Understanding","created":"2023-03-31","cited_by_count":48,"area":null},{"id":"2401.04350","title":"Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness","created":"2024-01-09","cited_by_count":48,"area":"mllm"},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45,"area":null},{"id":"2304.04227","title":"Video ChatCaptioner: Towards Enriched Spatiotemporal Descriptions","created":"2023-04-09","cited_by_count":42,"area":null},{"id":"2305.10683","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","created":"2023-05-18","cited_by_count":42,"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":"2403.13347","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","created":"2024-03-20","cited_by_count":41,"area":null},{"id":"2302.06605","title":"UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling","created":"2023-02-13","cited_by_count":40,"area":"mllm"},{"id":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"area":null},{"id":"2309.13952","title":"VidChapters-7M: Video Chapters at Scale","created":"2023-09-25","cited_by_count":39,"area":null},{"id":"2505.00337","title":"T2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video Generation","created":"2025-05-01","cited_by_count":39,"area":null},{"id":"2306.04362","title":"Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks","created":"2023-06-07","cited_by_count":36,"area":"mllm"},{"id":"2308.07648","title":"Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval","created":"2023-08-15","cited_by_count":35,"area":null},{"id":"2308.03135","title":"EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-world Understanding","created":"2023-08-06","cited_by_count":34,"area":"mllm"},{"id":"2406.19255","title":"Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment","created":"2024-06-27","cited_by_count":32,"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":"2311.07022","title":"ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models","created":"2023-11-13","cited_by_count":26,"area":null},{"id":"2207.11100","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens","created":"2022-07-22","cited_by_count":25,"area":null},{"id":"2305.08381","title":"Parameter-efficient Tuning of Large-scale Multimodal Foundation Model","created":"2023-05-15","cited_by_count":23,"area":null},{"id":"2302.00268","title":"Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection","created":"2023-02-01","cited_by_count":22,"area":"mllm"},{"id":"2307.06166","title":"Can Vision-Language Models be a Good Guesser? Exploring VLMs for Times and Location Reasoning","created":"2023-07-12","cited_by_count":22,"area":"lr"},{"id":"2403.17935","title":"OmniVid: A Generative Framework for Universal Video Understanding","created":"2024-03-26","cited_by_count":22,"area":null},{"id":"2212.03490","title":"SimVTP: Simple Video Text Pre-training with Masked Autoencoders","created":"2022-12-07","cited_by_count":21,"area":null},{"id":"2307.12964","title":"Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment","created":"2023-07-24","cited_by_count":21,"area":null},{"id":"2311.12919","title":"SPOT! Revisiting Video-Language Models for Event Understanding","created":"2023-11-21","cited_by_count":20,"area":null},{"id":"2204.03382","title":"Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations","created":"2022-04-07","cited_by_count":19,"area":null},{"id":"2312.14667","title":"Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition","created":"2023-12-22","cited_by_count":18,"area":null},{"id":"2405.19387","title":"Video Anomaly Detection in 10 Years: A Survey and Outlook","created":"2024-05-29","cited_by_count":18,"area":null},{"id":"2305.13167","title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending","created":"2023-05-22","cited_by_count":17,"area":null},{"id":"2210.11929","title":"LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling","created":"2022-10-21","cited_by_count":16,"area":null},{"id":"2410.15364","title":"Scene Graph Generation with Role-Playing Large Language Models","created":"2024-10-20","cited_by_count":16,"area":"mllm"},{"id":"2211.11446","title":"SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training","created":"2022-11-21","cited_by_count":15,"area":null},{"id":"2303.13009","title":"MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models","created":"2023-03-23","cited_by_count":15,"area":null},{"id":"2308.11551","title":"Multi-event Video-Text Retrieval","created":"2023-08-22","cited_by_count":15,"area":null},{"id":"2311.05698","title":"Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities","created":"2023-11-09","cited_by_count":15,"area":null},{"id":"2403.01560","title":"XOV-Action: Towards Generalizable Open-Vocabulary Action Recognition","created":"2024-03-03","cited_by_count":15,"area":null},{"id":"2211.13437","title":"Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning","created":"2022-11-24","cited_by_count":14,"area":"mllm"},{"id":"2305.14173","title":"TVTSv2: Learning Out-of-the-box Spatiotemporal Visual Representations at Scale","created":"2023-05-23","cited_by_count":14,"area":null},{"id":"2301.07463","title":"Temporal Perceiving Video-Language Pre-training","created":"2023-01-18","cited_by_count":12,"area":null},{"id":"2306.07096","title":"Global and Local Semantic Completion Learning for Vision-Language Pre-training","created":"2023-06-12","cited_by_count":12,"area":"mllm"},{"id":"2308.02982","title":"Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation","created":"2023-08-06","cited_by_count":12,"area":"mllm"},{"id":"2308.10402","title":"Simple Baselines for Interactive Video Retrieval with Questions and Answers","created":"2023-08-21","cited_by_count":12,"area":null},{"id":"2408.02687","title":"Compositional Physical Reasoning of Objects and Events from Videos","created":"2024-08-02","cited_by_count":12,"area":null},{"id":"2212.00986","title":"Masked Contrastive Pre-Training for Efficient Video-Text Retrieval","created":"2022-12-02","cited_by_count":11,"area":null},{"id":"2304.08809","title":"SViTT: Temporal Learning of Sparse Video-Text Transformers","created":"2023-04-18","cited_by_count":11,"area":null},{"id":"2306.09085","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","created":"2023-06-15","cited_by_count":11,"area":"mllm"},{"id":"2406.14481","title":"Revealing Vision-Language Integration in the Brain with Multimodal Networks","created":"2024-06-20","cited_by_count":11,"area":null},{"id":"2502.13363","title":"Pretrained Image-Text Models are Secretly Video Captioners","created":"2025-02-19","cited_by_count":11,"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":"2312.08984","title":"CL2CM: Improving Cross-Lingual Cross-Modal Retrieval via Cross-Lingual Knowledge Transfer","created":"2023-12-14","cited_by_count":10,"area":null},{"id":"2211.12402","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","created":"2022-11-22","cited_by_count":9,"area":"mllm"},{"id":"2311.17951","title":"C3Net: Compound Conditioned ControlNet for Multimodal Content Generation","created":"2023-11-29","cited_by_count":8,"area":null},{"id":"2407.07478","title":"EA-VTR: Event-Aware Video-Text Retrieval","created":"2024-07-10","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":"2308.09363","title":"Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models","created":"2023-08-18","cited_by_count":7,"area":null},{"id":"2302.05016","title":"Is Multimodal Vision Supervision Beneficial to Language?","created":"2023-02-10","cited_by_count":6,"area":null},{"id":"2302.08063","title":"MINOTAUR: Multi-task Video Grounding From Multimodal Queries","created":"2023-02-16","cited_by_count":6,"area":null},{"id":"2305.10049","title":"TG-VQA: Ternary Game of Video Question Answering","created":"2023-05-17","cited_by_count":6,"area":null},{"id":"2311.00298","title":"An Empirical Study of Frame Selection for Text-to-Video Retrieval","created":"2023-11-01","cited_by_count":6,"area":null},{"id":"2412.06182","title":"Towards Long Video Understanding via Fine-detailed Video Story Generation","created":"2024-12-09","cited_by_count":6,"area":null},{"id":"2504.18856","title":"Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation","created":"2025-04-26","cited_by_count":6,"area":"mllm"},{"id":"2210.06881","title":"RaP: Redundancy-aware Video-language Pre-training for Text-Video Retrieval","created":"2022-10-13","cited_by_count":5,"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":"2309.15915","title":"Zero-Shot and Few-Shot Video Question Answering with Multi-Modal Prompts","created":"2023-09-27","cited_by_count":5,"area":"mllm"},{"id":"2404.00973","title":"VideoDistill: Language-aware Vision Distillation for Video Question Answering","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2410.09380","title":"Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering","created":"2024-10-12","cited_by_count":5,"area":null},{"id":"2506.14107","title":"D\\'ej\\`a Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2302.02136","title":"Efficient End-to-End Video Question Answering with Pyramidal Multimodal Transformer","created":"2023-02-04","cited_by_count":4,"area":null},{"id":"2308.12960","title":"Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment","created":"2023-08-24","cited_by_count":4,"area":"mllm"},{"id":"2401.04023","title":"Efficient Multiscale Multimodal Bottleneck Transformer for Audio-Video Classification","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2401.07669","title":"SRL-CLIP: Efficient CLIP Video Adaptation via Structured Semantic Role Labels","created":"2024-01-15","cited_by_count":4,"area":null}],"next_cursor":"100"}