{"list":"other","total":77,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"2310.14566","title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","created":"2023-10-23","cited_by_count":583},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"1812.08658","title":"nocaps: novel object captioning at scale","created":"2018-12-20","cited_by_count":444},{"id":"1904.03493","title":"VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research","created":"2019-04-06","cited_by_count":414},{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"2403.00476","title":"TempCompass: Do Video LLMs Really Understand Videos?","created":"2024-03-01","cited_by_count":363},{"id":"2403.10517","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","created":"2024-03-15","cited_by_count":332},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326},{"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},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"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},{"id":"1603.03925","title":"Image Captioning with Semantic Attention","created":"2016-03-12","cited_by_count":260},{"id":"2012.00451","title":"Just Ask: Learning to Answer Questions from Millions of Narrated Videos","created":"2020-12-01","cited_by_count":248},{"id":"2311.16839","title":"Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization","created":"2023-11-28","cited_by_count":225},{"id":"1810.04020","title":"A Comprehensive Survey of Deep Learning for Image Captioning","created":"2018-10-06","cited_by_count":214},{"id":"1604.03968","title":"Visual Storytelling","created":"2016-04-13","cited_by_count":176},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169},{"id":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140},{"id":"1904.04289","title":"SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition","created":"2019-04-08","cited_by_count":134},{"id":"2206.03428","title":"Revealing Single Frame Bias for Video-and-Language Learning","created":"2022-06-07","cited_by_count":133},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120},{"id":"1609.06647","title":"Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge","created":"2016-09-21","cited_by_count":116},{"id":"1808.10584","title":"Learning to Describe Differences Between Pairs of Similar Images","created":"2018-08-31","cited_by_count":114},{"id":"2410.10818","title":"TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models","created":"2024-10-14","cited_by_count":97},{"id":"2301.00184","title":"Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?","created":"2022-12-31","cited_by_count":90},{"id":"2406.16338","title":"VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models","created":"2024-06-24","cited_by_count":90},{"id":"2402.13250","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","created":"2024-02-20","cited_by_count":89},{"id":"2404.01297","title":"Streaming Dense Video Captioning","created":"2024-04-01","cited_by_count":82},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76},{"id":"1907.08340","title":"Only Time Can Tell: Discovering Temporal Data for Temporal Modeling","created":"2019-07-19","cited_by_count":67},{"id":"1611.04021","title":"Leveraging Video Descriptions to Learn Video Question Answering","created":"2016-11-12","cited_by_count":55},{"id":"2311.17404","title":"VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models","created":"2023-11-29","cited_by_count":55},{"id":"1510.07712","title":"Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks","created":"2015-10-26","cited_by_count":54},{"id":"2312.02974","title":"Describing Differences in Image Sets with Natural Language","created":"2023-12-05","cited_by_count":53},{"id":"2406.19392","title":"ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos","created":"2024-06-27","cited_by_count":51},{"id":"2303.16899","title":"AutoAD: Movie Description in Context","created":"2023-03-29","cited_by_count":50},{"id":"2309.10091","title":"Unified Coarse-to-Fine Alignment for Video-Text Retrieval","created":"2023-09-18","cited_by_count":49},{"id":"2310.06838","title":"AutoAD II: The Sequel -- Who, When, and What in Movie Audio Description","created":"2023-10-10","cited_by_count":49},{"id":"2404.12353","title":"V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning","created":"2024-04-18","cited_by_count":46},{"id":"2312.11782","title":"Learning Object State Changes in Videos: An Open-World Perspective","created":"2023-12-19","cited_by_count":36},{"id":"2404.14412","title":"AutoAD III: The Prequel -- Back to the Pixels","created":"2024-04-22","cited_by_count":35},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28},{"id":"2407.16772","title":"VisMin: Visual Minimal-Change Understanding","created":"2024-07-23","cited_by_count":23},{"id":"1807.09418","title":"Video Storytelling: Textual Summaries for Events","created":"2018-07-25","cited_by_count":22},{"id":"2308.10417","title":"The Change You Want to See (Now in 3D)","created":"2023-08-21","cited_by_count":17},{"id":"2408.04594","title":"Img-Diff: Contrastive Data Synthesis for Multimodal Large Language Models","created":"2024-08-08","cited_by_count":17},{"id":"2402.17128","title":"OSCaR: Object State Captioning and State Change Representation","created":"2024-02-27","cited_by_count":16},{"id":"2406.06499","title":"NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative","created":"2024-06-10","cited_by_count":10},{"id":"2410.11702","title":"It's Just Another Day: Unique Video Captioning by Discriminative Prompting","created":"2024-10-15","cited_by_count":3}],"next_cursor":null}