{"list":"other","total":77,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"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":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"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":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"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":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"id":"2006.06666","title":"VirTex: Learning Visual Representations from Textual Annotations","created":"2020-06-11","cited_by_count":339},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"1903.08225","title":"Cross-task weakly supervised learning from instructional videos","created":"2019-03-19","cited_by_count":199},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130},{"id":"1804.09627","title":"Actor and Observer: Joint Modeling of First and Third-Person Videos","created":"2018-04-25","cited_by_count":103},{"id":"1904.06807","title":"Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation","created":"2019-04-15","cited_by_count":97},{"id":"2403.16182","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","created":"2024-03-24","cited_by_count":95},{"id":"2306.07915","title":"Image Captioners Are Scalable Vision Learners Too","created":"2023-06-13","cited_by_count":89},{"id":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72},{"id":"2308.08428","title":"ALIP: Adaptive Language-Image Pre-training with Synthetic Caption","created":"2023-08-16","cited_by_count":70},{"id":"2303.07284","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","created":"2023-03-13","cited_by_count":65},{"id":"1804.08366","title":"VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometry","created":"2018-04-23","cited_by_count":61},{"id":"1702.08272","title":"A Dataset for Developing and Benchmarking Active Vision","created":"2017-02-27","cited_by_count":50},{"id":"1806.03107","title":"Temporal Difference Variational Auto-Encoder","created":"2018-06-08","cited_by_count":49},{"id":"2106.03336","title":"Wide-Baseline Relative Camera Pose Estimation with Directional Learning","created":"2021-06-07","cited_by_count":49},{"id":"2007.15781","title":"LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities","created":"2020-07-31","cited_by_count":47},{"id":"2301.00746","title":"NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory","created":"2023-01-02","cited_by_count":46},{"id":"2104.13530","title":"Extreme Rotation Estimation using Dense Correlation Volumes","created":"2021-04-28","cited_by_count":42},{"id":"1709.00507","title":"Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks","created":"2017-09-01","cited_by_count":38},{"id":"1808.07784","title":"Time-Agnostic Prediction: Predicting Predictable Video Frames","created":"2018-08-23","cited_by_count":37},{"id":"1805.12174","title":"Video Summarization by Learning from Unpaired Data","created":"2018-05-30","cited_by_count":36},{"id":"2208.06773","title":"TL;DW? Summarizing Instructional Videos with Task Relevance & Cross-Modal Saliency","created":"2022-08-14","cited_by_count":35},{"id":"2007.08809","title":"SumGraph: Video Summarization via Recursive Graph Modeling","created":"2020-07-17","cited_by_count":32},{"id":"1907.10164","title":"Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection","created":"2019-07-23","cited_by_count":31},{"id":"1510.01442","title":"Unsupervised Extraction of Video Highlights Via Robust Recurrent Auto-encoders","created":"2015-10-06","cited_by_count":30},{"id":"2205.05019","title":"Learning to Answer Visual Questions from Web Videos","created":"2022-05-10","cited_by_count":30},{"id":"1805.02838","title":"A Memory Network Approach for Story-based Temporal Summarization of 360{\\deg} Videos","created":"2018-05-08","cited_by_count":29},{"id":"2301.00805","title":"Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation","created":"2023-01-02","cited_by_count":28},{"id":"2012.02356","title":"WeaQA: Weak Supervision via Captions for Visual Question Answering","created":"2020-12-04","cited_by_count":25},{"id":"1612.02335","title":"Pano2Vid: Automatic Cinematography for Watching 360$^{\\circ}$ Videos","created":"2016-12-07","cited_by_count":22},{"id":"1705.01759","title":"Deep 360 Pilot: Learning a Deep Agent for Piloting through 360{\\deg} Sports Video","created":"2017-05-04","cited_by_count":22},{"id":"2007.09598","title":"Adaptive Video Highlight Detection by Learning from User History","created":"2020-07-19","cited_by_count":22},{"id":"2207.11365","title":"EgoEnv: Human-centric environment representations from egocentric video","created":"2022-07-22","cited_by_count":22},{"id":"1505.04803","title":"Predicting Important Objects for Egocentric Video Summarization","created":"2015-05-18","cited_by_count":21},{"id":"1811.01292","title":"Geometry-Aware Recurrent Neural Networks for Active Visual Recognition","created":"2018-11-03","cited_by_count":20},{"id":"1605.00164","title":"Look-ahead before you leap: end-to-end active recognition by forecasting the effect of motion","created":"2016-04-30","cited_by_count":18},{"id":"1706.03114","title":"Collaborative Summarization of Topic-Related Videos","created":"2017-06-09","cited_by_count":17},{"id":"2303.16891","title":"Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations","created":"2023-03-29","cited_by_count":16},{"id":"1906.11407","title":"Emergence of Exploratory Look-Around Behaviors through Active Observation Completion","created":"2019-06-27","cited_by_count":14},{"id":"1703.00495","title":"Making 360$^{\\circ}$ Video Watchable in 2D: Learning Videography for Click Free Viewing","created":"2017-03-01","cited_by_count":13},{"id":"1807.04219","title":"How Local is the Local Diversity? Reinforcing Sequential Determinantal Point Processes with Dynamic Ground Sets for Supervised Video Summarization","created":"2018-07-11","cited_by_count":13},{"id":"2404.07336","title":"PEAVS: Perceptual Evaluation of Audio-Visual Synchrony Grounded in Viewers' Opinion Scores","created":"2024-04-10","cited_by_count":13},{"id":"1808.04768","title":"Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models","created":"2018-08-14","cited_by_count":12},{"id":"2404.05016","title":"Hyperbolic Learning with Synthetic Captions for Open-World Detection","created":"2024-04-07","cited_by_count":12},{"id":"1807.11010","title":"Sidekick Policy Learning for Active Visual Exploration","created":"2018-07-29","cited_by_count":11},{"id":"1509.07225","title":"Automatic Concept Discovery from Parallel Text and Visual Corpora","created":"2015-09-24","cited_by_count":10},{"id":"2007.11548","title":"Attend and Segment: Attention Guided Active Semantic Segmentation","created":"2020-07-22","cited_by_count":9},{"id":"2108.11717","title":"Glimpse-Attend-and-Explore: Self-Attention for Active Visual Exploration","created":"2021-08-26","cited_by_count":9},{"id":"1812.00108","title":"Multi-Stream Dynamic Video Summarization","created":"2018-12-01","cited_by_count":8},{"id":"1809.02854","title":"Learning Sports Camera Selection from Internet Videos","created":"2018-09-08","cited_by_count":6},{"id":"1706.03121","title":"Multi-View Surveillance Video Summarization via Joint Embedding and Sparse Optimization","created":"2017-06-09","cited_by_count":5},{"id":"2110.01774","title":"HighlightMe: Detecting Highlights from Human-Centric Videos","created":"2021-10-05","cited_by_count":3},{"id":"1711.08664","title":"Self-view Grounding Given a Narrated 360{\\deg} Video","created":"2017-11-23","cited_by_count":2}],"next_cursor":null}