{"list":"other","total":63,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"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":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"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":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"id":"2306.01567","title":"Segment Anything in High Quality","created":"2023-06-02","cited_by_count":376},{"id":"1903.01945","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","created":"2019-03-05","cited_by_count":373},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"1903.08225","title":"Cross-task weakly supervised learning from instructional videos","created":"2019-03-19","cited_by_count":199},{"id":"1505.04474","title":"Visual Semantic Role Labeling","created":"2015-05-17","cited_by_count":190},{"id":"1808.07962","title":"Learning Human-Object Interactions by Graph Parsing Neural Networks","created":"2018-08-23","cited_by_count":176},{"id":"2110.08568","title":"ASFormer: Transformer for Action Segmentation","created":"2021-10-16","cited_by_count":168},{"id":"2309.17024","title":"HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World","created":"2023-09-29","cited_by_count":166},{"id":"1912.12898","title":"PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection","created":"2019-12-30","cited_by_count":143},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140},{"id":"2411.19167","title":"HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos","created":"2024-11-28","cited_by_count":129},{"id":"1808.10437","title":"iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection","created":"2018-08-30","cited_by_count":127},{"id":"2111.13216","title":"Cross-Domain Adaptive Teacher for Object Detection","created":"2021-11-25","cited_by_count":126},{"id":"1906.11415","title":"Few-Shot Video Classification via Temporal Alignment","created":"2019-06-27","cited_by_count":125},{"id":"2007.00394","title":"The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose","created":"2020-07-01","cited_by_count":95},{"id":"1907.01172","title":"Procedure Planning in Instructional Videos","created":"2019-07-02","cited_by_count":92},{"id":"2112.01838","title":"Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer","created":"2021-12-03","cited_by_count":91},{"id":"2210.10352","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","created":"2022-10-19","cited_by_count":85},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84},{"id":"1901.02598","title":"D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation","created":"2019-01-09","cited_by_count":83},{"id":"2207.10883","title":"My View is the Best View: Procedure Learning from Egocentric Videos","created":"2022-07-22","cited_by_count":81},{"id":"2208.03826","title":"Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications","created":"2022-08-07","cited_by_count":78},{"id":"2303.17959","title":"Diffusion Action Segmentation","created":"2023-03-31","cited_by_count":74},{"id":"2006.00626","title":"In the Eye of the Beholder: Gaze and Actions in First Person Video","created":"2020-05-31","cited_by_count":69},{"id":"2104.09496","title":"Temporal Query Networks for Fine-grained Video Understanding","created":"2021-04-19","cited_by_count":68},{"id":"2110.01770","title":"Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning","created":"2021-10-05","cited_by_count":53},{"id":"2312.14556","title":"CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities","created":"2023-12-22","cited_by_count":51},{"id":"2212.06200","title":"Breaking the \"Object\" in Video Object Segmentation","created":"2022-12-12","cited_by_count":49},{"id":"2310.17323","title":"IndustReal: A Dataset for Procedure Step Recognition Handling Execution Errors in Egocentric Videos in an Industrial-Like Setting","created":"2023-10-26","cited_by_count":48},{"id":"2108.11996","title":"Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers","created":"2021-08-26","cited_by_count":39},{"id":"2304.13265","title":"StepFormer: Self-supervised Step Discovery and Localization in Instructional Videos","created":"2023-04-26","cited_by_count":37},{"id":"1906.01028","title":"A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation","created":"2019-06-03","cited_by_count":36},{"id":"2209.08691","title":"MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain","created":"2022-09-19","cited_by_count":36},{"id":"2308.11358","title":"How Much Temporal Long-Term Context is Needed for Action Segmentation?","created":"2023-08-22","cited_by_count":36},{"id":"2307.08763","title":"Video-Mined Task Graphs for Keystep Recognition in Instructional Videos","created":"2023-07-17","cited_by_count":35},{"id":"2207.14192","title":"Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection","created":"2022-07-28","cited_by_count":34},{"id":"2105.10859","title":"Coarse to Fine Multi-Resolution Temporal Convolutional Network","created":"2021-05-23","cited_by_count":28},{"id":"2303.13519","title":"Learning and Verification of Task Structure in Instructional Videos","created":"2023-03-23","cited_by_count":26},{"id":"2406.01486","title":"Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos","created":"2024-06-03","cited_by_count":26},{"id":"2112.01402","title":"Iterative Contrast-Classify For Semi-supervised Temporal Action Segmentation","created":"2021-12-02","cited_by_count":19},{"id":"2306.12152","title":"Exploiting Multimodal Synthetic Data for Egocentric Human-Object Interaction Detection in an Industrial Scenario","created":"2023-06-21","cited_by_count":14},{"id":"2110.11524","title":"Sequential Voting with Relational Box Fields for Active Object Detection","created":"2021-10-21","cited_by_count":13},{"id":"2309.14809","title":"ENIGMA-51: Towards a Fine-Grained Understanding of Human-Object Interactions in Industrial Scenarios","created":"2023-09-26","cited_by_count":11},{"id":"2312.02672","title":"Are Synthetic Data Useful for Egocentric Hand-Object Interaction Detection?","created":"2023-12-05","cited_by_count":10},{"id":"2109.14734","title":"Egocentric Hand-object Interaction Detection and Application","created":"2021-09-29","cited_by_count":7}],"next_cursor":null}