{"list":"other","total":101,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"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":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"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":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"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":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"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":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"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":"1711.09577","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","created":"2017-11-27","cited_by_count":551},{"id":"2311.17043","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","created":"2023-11-28","cited_by_count":546},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"1810.11981","title":"GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild","created":"2018-10-29","cited_by_count":475},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"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":"1904.00607","title":"Video Object Segmentation using Space-Time Memory Networks","created":"2019-04-01","cited_by_count":438},{"id":"1809.07845","title":"LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking","created":"2018-09-20","cited_by_count":429},{"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":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"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":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"2306.00989","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","created":"2023-06-01","cited_by_count":290},{"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":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234},{"id":"2306.07207","title":"Valley: Video Assistant with Large Language model Enhanced abilitY","created":"2023-06-12","cited_by_count":234},{"id":"2308.08544","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","created":"2023-08-16","cited_by_count":228},{"id":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226},{"id":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225},{"id":"1902.03604","title":"MOTS: Multi-Object Tracking and Segmentation","created":"2019-02-10","cited_by_count":223},{"id":"2308.02487","title":"Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP","created":"2023-08-04","cited_by_count":201},{"id":"1912.07515","title":"Learning a Neural Solver for Multiple Object Tracking","created":"2019-12-16","cited_by_count":198},{"id":"2310.12982","title":"Putting the Object Back into Video Object Segmentation","created":"2023-10-19","cited_by_count":188},{"id":"2312.06709","title":"AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One","created":"2023-12-10","cited_by_count":169},{"id":"1803.08006","title":"Video Object Segmentation with Language Referring Expressions","created":"2018-03-21","cited_by_count":162},{"id":"2312.10032","title":"Osprey: Pixel Understanding with Visual Instruction Tuning","created":"2023-12-15","cited_by_count":159},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154},{"id":"2005.10356","title":"TAO: A Large-Scale Benchmark for Tracking Any Object","created":"2020-05-20","cited_by_count":147},{"id":"2006.11339","title":"Video Panoptic Segmentation","created":"2020-06-19","cited_by_count":142},{"id":"2010.07548","title":"MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking","created":"2020-10-15","cited_by_count":136},{"id":"2104.04691","title":"Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation","created":"2021-04-10","cited_by_count":133},{"id":"2407.11325","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","created":"2024-07-16","cited_by_count":127},{"id":"2407.15841","title":"SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models","created":"2024-07-22","cited_by_count":125},{"id":"1604.02748","title":"TGIF: A New Dataset and Benchmark on Animated GIF Description","created":"2016-04-10","cited_by_count":124},{"id":"1503.01313","title":"A Novel Performance Evaluation Methodology for Single-Target Trackers","created":"2015-03-04","cited_by_count":113},{"id":"1803.07485","title":"Actor and Action Video Segmentation from a Sentence","created":"2018-03-20","cited_by_count":106},{"id":"2309.12871","title":"AnglE-optimized Text Embeddings","created":"2023-09-22","cited_by_count":99},{"id":"2207.10661","title":"In Defense of Online Models for Video Instance Segmentation","created":"2022-07-21","cited_by_count":97},{"id":"2012.05258","title":"ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation","created":"2020-12-09","cited_by_count":96},{"id":"2206.04403","title":"VITA: Video Instance Segmentation via Object Token Association","created":"2022-06-09","cited_by_count":94},{"id":"1911.11206","title":"Oops! Predicting Unintentional Action in Video","created":"2019-11-25","cited_by_count":82},{"id":"2404.01297","title":"Streaming Dense Video Captioning","created":"2024-04-01","cited_by_count":82},{"id":"2102.11859","title":"STEP: Segmenting and Tracking Every Pixel","created":"2021-02-23","cited_by_count":73},{"id":"2312.17240","title":"LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model","created":"2023-12-28","cited_by_count":71},{"id":"2209.12118","title":"BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video","created":"2022-09-25","cited_by_count":66},{"id":"2206.07704","title":"Waymo Open Dataset: Panoramic Video Panoptic Segmentation","created":"2022-06-15","cited_by_count":58},{"id":"2404.03645","title":"Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation","created":"2024-04-04","cited_by_count":55},{"id":"2307.15958","title":"XMem++: Production-level Video Segmentation From Few Annotated Frames","created":"2023-07-29","cited_by_count":53},{"id":"2212.03229","title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning","created":"2022-12-06","cited_by_count":49},{"id":"2312.13305","title":"DVIS++: Improved Decoupled Framework for Universal Video Segmentation","created":"2023-12-20","cited_by_count":46},{"id":"2304.01715","title":"Towards Open-Vocabulary Video Instance Segmentation","created":"2023-04-04","cited_by_count":45},{"id":"2207.12978","title":"Tracking Every Thing in the Wild","created":"2022-07-26","cited_by_count":44},{"id":"2205.15361","title":"TubeFormer-DeepLab: Video Mask Transformer","created":"2022-05-30","cited_by_count":35},{"id":"2302.11217","title":"Connecting Vision and Language with Video Localized Narratives","created":"2023-02-22","cited_by_count":24},{"id":"2304.04694","title":"Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation","created":"2023-04-10","cited_by_count":24},{"id":"2404.08639","title":"COCONut: Modernizing COCO Segmentation","created":"2024-04-12","cited_by_count":24},{"id":"2112.09131","title":"HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images","created":"2021-12-16","cited_by_count":21},{"id":"2101.06545","title":"VideoClick: Video Object Segmentation with a Single Click","created":"2021-01-16","cited_by_count":8}],"next_cursor":"100"}