{"list":"other","total":65,"rows":[{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"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":"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":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"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":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"2002.11949","title":"Unbiased Scene Graph Generation from Biased Training","created":"2020-02-27","cited_by_count":356},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"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":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"2304.11968","title":"Track Anything: Segment Anything Meets Videos","created":"2023-04-24","cited_by_count":234},{"id":"2305.06558","title":"Segment and Track Anything","created":"2023-05-11","cited_by_count":193},{"id":"1605.03705","title":"Movie Description","created":"2016-05-12","cited_by_count":181},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120},{"id":"2201.08264","title":"End-to-end Generative Pretraining for Multimodal Video Captioning","created":"2022-01-20","cited_by_count":116},{"id":"2312.02949","title":"LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models","created":"2023-12-05","cited_by_count":113},{"id":"2409.19603","title":"One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos","created":"2024-09-29","cited_by_count":100},{"id":"2203.16434","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","created":"2022-03-30","cited_by_count":98},{"id":"1902.11266","title":"Efficient Parameter-free Clustering Using First Neighbor Relations","created":"2019-02-28","cited_by_count":97},{"id":"1807.10982","title":"Actor-Centric Relation Network","created":"2018-07-28","cited_by_count":87},{"id":"2404.01297","title":"Streaming Dense Video Captioning","created":"2024-04-01","cited_by_count":82},{"id":"1712.06761","title":"MovieGraphs: Towards Understanding Human-Centric Situations from Videos","created":"2017-12-19","cited_by_count":67},{"id":"2104.00990","title":"Visual Semantic Role Labeling for Video Understanding","created":"2021-04-02","cited_by_count":60},{"id":"2307.15958","title":"XMem++: Production-level Video Segmentation From Few Annotated Frames","created":"2023-07-29","cited_by_count":53},{"id":"2311.13435","title":"PG-Video-LLaVA: Pixel Grounding Large Video-Language Models","created":"2023-11-22","cited_by_count":51},{"id":"2411.04923","title":"VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos","created":"2024-11-07","cited_by_count":51},{"id":"2510.20579","title":"Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence","created":"2025-10-23","cited_by_count":49},{"id":"2311.17058","title":"Panoptic Video Scene Graph Generation","created":"2023-11-28","cited_by_count":46},{"id":"2109.04127","title":"Word-Level Coreference Resolution","created":"2021-09-09","cited_by_count":40},{"id":"2312.00937","title":"Zero-Shot Video Question Answering with Procedural Programs","created":"2023-12-01","cited_by_count":37},{"id":"2211.12142","title":"Coreference Resolution through a seq2seq Transition-Based System","created":"2022-11-22","cited_by_count":34},{"id":"2003.10606","title":"Video Object Grounding using Semantic Roles in Language Description","created":"2020-03-24","cited_by_count":25},{"id":"2312.03050","title":"HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding","created":"2023-12-05","cited_by_count":22},{"id":"2109.12776","title":"Joint Multimedia Event Extraction from Video and Article","created":"2021-09-27","cited_by_count":19},{"id":"2308.05081","title":"Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling","created":"2023-08-09","cited_by_count":15},{"id":"2008.09791","title":"Identity-Aware Multi-Sentence Video Description","created":"2020-08-22","cited_by_count":13},{"id":"2210.10828","title":"Grounded Video Situation Recognition","created":"2022-10-19","cited_by_count":13},{"id":"2405.11483","title":"MICap: A Unified Model for Identity-aware Movie Descriptions","created":"2024-05-19","cited_by_count":9},{"id":"2406.14654","title":"Major Entity Identification: A Generalizable Alternative to Coreference Resolution","created":"2024-06-20","cited_by_count":9},{"id":"2211.01781","title":"Video Event Extraction via Tracking Visual States of Arguments","created":"2022-11-03","cited_by_count":8},{"id":"2211.14563","title":"Who are you referring to? Coreference resolution in image narrations","created":"2022-11-26","cited_by_count":7},{"id":"2310.13619","title":"Semi-supervised multimodal coreference resolution in image narrations","created":"2023-10-20","cited_by_count":4},{"id":"2407.20642","title":"Effectively Leveraging CLIP for Generating Situational Summaries of Images and Videos","created":"2024-07-30","cited_by_count":2}],"next_cursor":null}