{"total":124,"rows":[{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771,"area":null},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744,"area":null},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658,"area":"wm"},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484,"area":null},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447,"area":null},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388,"area":null},{"id":"2410.17434","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","created":"2024-10-22","cited_by_count":356,"area":"mllm"},{"id":"2404.16994","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","created":"2024-04-25","cited_by_count":322,"area":"mllm"},{"id":"2409.04429","title":"VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation","created":"2024-09-06","cited_by_count":295,"area":"diffusion"},{"id":"2504.05299","title":"SmolVLM: Redefining small and efficient multimodal models","created":"2025-04-07","cited_by_count":237,"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":"2503.05236","title":"Unified Reward Model for Multimodal Understanding and Generation","created":"2025-03-07","cited_by_count":199,"area":"alignment"},{"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":"2412.01818","title":"Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs","created":"2024-12-02","cited_by_count":157,"area":"mllm"},{"id":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"area":null},{"id":"2407.15841","title":"SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models","created":"2024-07-22","cited_by_count":125,"area":null},{"id":"2403.18406","title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","created":"2024-03-27","cited_by_count":97,"area":"lr"},{"id":"2209.15323","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","created":"2022-09-30","cited_by_count":82,"area":null},{"id":"2103.10699","title":"MDMMT: Multidomain Multimodal Transformer for Video Retrieval","created":"2021-03-19","cited_by_count":78,"area":null},{"id":"2311.18834","title":"ART$\\boldsymbol{\\cdot}$V: Auto-Regressive Text-to-Video Generation with Diffusion Models","created":"2023-11-30","cited_by_count":76,"area":"diffusion"},{"id":"2410.23266","title":"TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models","created":"2024-10-30","cited_by_count":73,"area":"lr"},{"id":"2406.11303","title":"VideoVista: A Versatile Benchmark for Video Understanding and Reasoning","created":"2024-06-17","cited_by_count":72,"area":"mllm"},{"id":"2101.11796","title":"DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents","created":"2021-01-28","cited_by_count":70,"area":null},{"id":"2205.14895","title":"From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering","created":"2022-05-30","cited_by_count":51,"area":"lr"},{"id":"2311.13435","title":"PG-Video-LLaVA: Pixel Grounding Large Video-Language Models","created":"2023-11-22","cited_by_count":51,"area":"mllm"},{"id":"2309.03549","title":"Reuse and Diffuse: Iterative Denoising for Text-to-Video Generation","created":"2023-09-07","cited_by_count":50,"area":"diffusion"},{"id":"2205.05256","title":"Evaluation Gaps in Machine Learning Practice","created":"2022-05-11","cited_by_count":49,"area":null},{"id":"2412.19806","title":"Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing","created":"2024-10-08","cited_by_count":49,"area":null},{"id":"2312.00937","title":"Zero-Shot Video Question Answering with Procedural Programs","created":"2023-12-01","cited_by_count":37,"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":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2112.04888","title":"A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer","created":"2021-12-09","cited_by_count":26,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2311.05348","title":"u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model","created":"2023-11-09","cited_by_count":24,"area":"mllm"},{"id":"2411.17221","title":"AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM","created":"2024-11-26","cited_by_count":24,"area":"mllm"},{"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":"2212.03490","title":"SimVTP: Simple Video Text Pre-training with Masked Autoencoders","created":"2022-12-07","cited_by_count":21,"area":null},{"id":"2510.13721","title":"NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching","created":"2025-10-15","cited_by_count":21,"area":"diffusion"},{"id":"2403.08755","title":"DAM: Dynamic Adapter Merging for Continual Video QA Learning","created":"2024-03-13","cited_by_count":19,"area":null},{"id":"2204.02547","title":"Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation","created":"2022-04-06","cited_by_count":18,"area":null},{"id":"2312.02310","title":"VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding","created":"2023-12-04","cited_by_count":18,"area":null},{"id":"2401.00849","title":"COSMO: COntrastive Streamlined MultimOdal Model with Interleaved Pre-Training","created":"2024-01-01","cited_by_count":18,"area":"mllm"},{"id":"2407.08101","title":"What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction","created":"2024-07-11","cited_by_count":18,"area":"mllm"},{"id":"2112.03572","title":"Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices","created":"2021-12-07","cited_by_count":17,"area":null},{"id":"2207.08625","title":"Unifying Event Detection and Captioning as Sequence Generation via Pre-Training","created":"2022-07-18","cited_by_count":17,"area":null},{"id":"2407.15350","title":"WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding","created":"2024-07-22","cited_by_count":17,"area":null},{"id":"2412.09754","title":"ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation","created":"2024-12-12","cited_by_count":17,"area":"mllm"},{"id":"2511.16449","title":"Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference","created":"2025-11-20","cited_by_count":17,"area":"vla"},{"id":"2505.13928","title":"LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts","created":"2025-05-20","cited_by_count":14,"area":null},{"id":"2211.03779","title":"CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering","created":"2022-11-07","cited_by_count":13,"area":null},{"id":"2411.14401","title":"Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding","created":"2024-11-21","cited_by_count":13,"area":"mllm"},{"id":"2101.05954","title":"Recent Advances in Video Question Answering: A Review of Datasets and Methods","created":"2021-01-15","cited_by_count":12,"area":null},{"id":"2104.04182","title":"FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation Framework","created":"2021-04-09","cited_by_count":12,"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":"2203.07086","title":"MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization","created":"2022-03-14","cited_by_count":10,"area":null},{"id":"2501.05067","title":"LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding","created":"2025-01-09","cited_by_count":10,"area":"mllm"},{"id":"2504.01328","title":"Slow-Fast Architecture for Video Multi-Modal Large Language Models","created":"2025-04-02","cited_by_count":10,"area":"mllm"},{"id":"2505.12098","title":"LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation","created":"2025-05-17","cited_by_count":10,"area":"mllm"},{"id":"2510.13251","title":"Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs","created":"2025-10-15","cited_by_count":10,"area":"mllm"},{"id":"2206.01017","title":"Structured Two-stream Attention Network for Video Question Answering","created":"2022-06-02","cited_by_count":9,"area":null},{"id":"2406.09646","title":"A Survey of Video Datasets for Grounded Event Understanding","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2411.11066","title":"TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models","created":"2024-11-17","cited_by_count":9,"area":"mllm"},{"id":"2412.04432","title":"Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation","created":"2024-12-05","cited_by_count":9,"area":"diffusion"},{"id":"2511.01169","title":"Web-Scale Collection of Video Data for 4D Animal Reconstruction","created":"2025-11-03","cited_by_count":9,"area":null},{"id":"2604.23950","title":"LearnPruner: Rethinking Attention-based Token Pruning in Vision Language Models","created":"2026-04-27","cited_by_count":9,"area":"lr"},{"id":"2401.11654","title":"ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition","created":"2024-01-22","cited_by_count":8,"area":null},{"id":"2209.01621","title":"Interactive Question Answering Systems: Literature Review","created":"2022-09-04","cited_by_count":7,"area":null},{"id":"2311.11865","title":"VLM-Eval: A General Evaluation on Video Large Language Models","created":"2023-11-20","cited_by_count":7,"area":null},{"id":"2412.00624","title":"VideoSAVi: Self-Aligned Video Language Models without Human Supervision","created":"2024-12-01","cited_by_count":7,"area":"alignment"},{"id":"2104.00285","title":"CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning","created":"2021-04-01","cited_by_count":6,"area":null},{"id":"2311.00556","title":"ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab","created":"2023-11-01","cited_by_count":6,"area":null},{"id":"2409.19532","title":"Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding","created":"2024-09-29","cited_by_count":6,"area":null},{"id":"2412.01132","title":"Eyes on the Road: State-of-the-Art Video Question Answering Models Assessment for Traffic Monitoring Tasks","created":"2024-12-02","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":"2203.16763","title":"CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2307.04192","title":"Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models","created":"2023-07-09","cited_by_count":5,"area":null},{"id":"2406.01601","title":"Backpropagation-Free Multi-modal On-Device Model Adaptation via Cloud-Device Collaboration","created":"2024-05-21","cited_by_count":5,"area":null},{"id":"2406.09412","title":"Explore the Limits of Omni-modal Pretraining at Scale","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2412.12833","title":"FocusChat: Text-guided Long Video Understanding via Spatiotemporal Information Filtering","created":"2024-12-17","cited_by_count":5,"area":"mllm"},{"id":"2108.02365","title":"Hybrid Reasoning Network for Video-based Commonsense Captioning","created":"2021-08-05","cited_by_count":4,"area":null},{"id":"2402.11812","title":"Interpretable Embedding for Ad-hoc Video Search","created":"2024-02-19","cited_by_count":4,"area":null},{"id":"2504.17821","title":"VideoVista-CulturalLingo: 360$^\\circ$ Horizons-Bridging Cultures, Languages, and Domains in Video Comprehension","created":"2025-04-23","cited_by_count":4,"area":"lr"},{"id":"2505.20638","title":"Music Audio-Visual Question Answering Requires Specialized Multimodal Designs","created":"2025-05-27","cited_by_count":4,"area":"mllm"},{"id":"2203.06356","title":"Taking an Emotional Look at Video Paragraph Captioning","created":"2022-03-12","cited_by_count":3,"area":null},{"id":"2204.08453","title":"Neural Space-filling Curves","created":"2022-04-18","cited_by_count":3,"area":null},{"id":"2207.00282","title":"(Un)likelihood Training for Interpretable Embedding","created":"2022-07-01","cited_by_count":3,"area":null},{"id":"2304.02080","title":"Scalable and Accurate Self-supervised Multimodal Representation Learning without Aligned Video and Text Data","created":"2023-04-04","cited_by_count":3,"area":null},{"id":"2309.02290","title":"ATM: Action Temporality Modeling for Video Question Answering","created":"2023-09-05","cited_by_count":3,"area":"lr"},{"id":"2310.02894","title":"Human-centric Behavior Description in Videos: New Benchmark and Model","created":"2023-10-04","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":"2503.09445","title":"Astrea: A MOE-based Visual Understanding Model with Progressive Alignment","created":"2025-03-12","cited_by_count":3,"area":"mllm"},{"id":"2507.15569","title":"DynImg: Key Frames with Visual Prompts are Good Representation for Multi-Modal Video Understanding","created":"2025-07-21","cited_by_count":3,"area":"mllm"},{"id":"2603.02098","title":"Efficient and High-Fidelity Omni Modality Retrieval","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2105.09967","title":"Happy Dance, Slow Clap: Using Reaction GIFs to Predict Induced Affect on Twitter","created":"2021-05-20","cited_by_count":2,"area":null},{"id":"2110.06827","title":"NoisyActions2M: A Multimedia Dataset for Video Understanding from Noisy Labels","created":"2021-10-13","cited_by_count":2,"area":null},{"id":"2210.03941","title":"Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling","created":"2022-10-08","cited_by_count":2,"area":null},{"id":"2405.17450","title":"The Power of Next-Frame Prediction for Learning Physical Laws","created":"2024-05-21","cited_by_count":2,"area":null},{"id":"2503.11205","title":"LLaVA-MLB: Mitigating and Leveraging Attention Bias for Training-Free Video LLMs","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2506.21586","title":"Can Vision Language Models Understand Mimed Actions?","created":"2025-06-17","cited_by_count":2,"area":"mllm"}],"next_cursor":"100"}