{"list":"other","total":87,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","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":"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":"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":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"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":"1803.00567","title":"Computational Optimal Transport","created":"2018-03-01","cited_by_count":780},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"1905.12681","title":"What Makes Training Multi-Modal Classification Networks Hard?","created":"2019-05-29","cited_by_count":344},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"2203.07303","title":"All in One: Exploring Unified Video-Language Pre-training","created":"2022-03-14","cited_by_count":171},{"id":"2204.00097","title":"TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization","created":"2022-03-31","cited_by_count":168},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148},{"id":"1904.05349","title":"H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions","created":"2019-04-10","cited_by_count":141},{"id":"1703.03329","title":"UntrimmedNets for Weakly Supervised Action Recognition and Detection","created":"2017-03-09","cited_by_count":130},{"id":"1804.09626","title":"Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos","created":"2018-04-25","cited_by_count":128},{"id":"2005.03860","title":"Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching","created":"2020-05-08","cited_by_count":126},{"id":"2005.02190","title":"Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video","created":"2020-05-04","cited_by_count":120},{"id":"2103.06818","title":"Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization","created":"2021-03-11","cited_by_count":113},{"id":"2001.04583","title":"EGO-TOPO: Environment Affordances from Egocentric Video","created":"2020-01-14","cited_by_count":111},{"id":"1905.09035","title":"What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention","created":"2019-05-22","cited_by_count":105},{"id":"1804.09627","title":"Actor and Observer: Joint Modeling of First and Third-Person Videos","created":"2018-04-25","cited_by_count":103},{"id":"2104.07905","title":"Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos","created":"2021-04-16","cited_by_count":99},{"id":"1904.11045","title":"Bridging the Domain Gap for Ground-to-Aerial Image Matching","created":"2019-04-24","cited_by_count":95},{"id":"1611.02155","title":"Spatiotemporal Residual Networks for Video Action Recognition","created":"2016-11-07","cited_by_count":91},{"id":"2106.05968","title":"Space-time Mixing Attention for Video Transformer","created":"2021-06-10","cited_by_count":84},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73},{"id":"1803.03396","title":"Cross-View Image Synthesis using Conditional GANs","created":"2018-03-09","cited_by_count":69},{"id":"2211.13222","title":"SVFormer: Semi-supervised Video Transformer for Action Recognition","created":"2022-11-23","cited_by_count":68},{"id":"1806.06157","title":"Object Level Visual Reasoning in Videos","created":"2018-06-16","cited_by_count":67},{"id":"2210.06031","title":"Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning","created":"2022-10-12","cited_by_count":59},{"id":"1811.10698","title":"LSTA: Long Short-Term Attention for Egocentric Action Recognition","created":"2018-11-26","cited_by_count":57},{"id":"1904.05250","title":"Next-Active-Object prediction from Egocentric Videos","created":"2019-04-10","cited_by_count":55},{"id":"1605.03688","title":"Going Deeper into First-Person Activity Recognition","created":"2016-05-12","cited_by_count":48},{"id":"2304.03195","title":"Micron-BERT: BERT-based Facial Micro-Expression Recognition","created":"2023-04-06","cited_by_count":43},{"id":"2203.11637","title":"Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos","created":"2022-03-22","cited_by_count":39},{"id":"2003.06958","title":"Vec2Face: Unveil Human Faces from their Blackbox Features in Face Recognition","created":"2020-03-16","cited_by_count":36},{"id":"2110.06178","title":"TAda! Temporally-Adaptive Convolutions for Video Understanding","created":"2021-10-12","cited_by_count":36},{"id":"2108.03267","title":"BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation","created":"2021-08-06","cited_by_count":31},{"id":"2203.10233","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","created":"2022-03-19","cited_by_count":31},{"id":"2304.02135","title":"FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding","created":"2023-04-04","cited_by_count":27},{"id":"2206.09852","title":"M&M Mix: A Multimodal Multiview Transformer Ensemble","created":"2022-06-20","cited_by_count":20},{"id":"1803.11217","title":"Joint Person Segmentation and Identification in Synchronized First- and Third-person Videos","created":"2018-03-29","cited_by_count":18},{"id":"1607.06986","title":"Ego2Top: Matching Viewers in Egocentric and Top-view Videos","created":"2016-07-24","cited_by_count":17},{"id":"2002.03219","title":"Exocentric to Egocentric Image Generation via Parallel Generative Adversarial Network","created":"2020-02-08","cited_by_count":17},{"id":"2006.03201","title":"Egocentric Object Manipulation Graphs","created":"2020-06-05","cited_by_count":17},{"id":"1911.10967","title":"Forecasting Human-Object Interaction: Joint Prediction of Motor Attention and Actions in First Person Video","created":"2019-11-25","cited_by_count":14},{"id":"2206.11895","title":"Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space","created":"2022-06-23","cited_by_count":13},{"id":"1905.00742","title":"Egocentric Hand Track and Object-based Human Action Recognition","created":"2019-05-02","cited_by_count":12},{"id":"2205.10738","title":"OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation","created":"2022-05-22","cited_by_count":12},{"id":"1812.00104","title":"From Third Person to First Person: Dataset and Baselines for Synthesis and Retrieval","created":"2018-12-01","cited_by_count":10},{"id":"2006.10386","title":"SceneAdapt: Scene-based domain adaptation for semantic segmentation using adversarial learning","created":"2020-06-18","cited_by_count":9},{"id":"1612.08153","title":"EgoReID: Cross-view Self-Identification and Human Re-identification in Egocentric and Surveillance Videos","created":"2016-12-24","cited_by_count":4},{"id":"1901.03728","title":"Anticipation and next action forecasting in video: an end-to-end model with memory","created":"2019-01-11","cited_by_count":4},{"id":"2304.07199","title":"CROVIA: Seeing Drone Scenes from Car Perspective via Cross-View Adaptation","created":"2023-04-14","cited_by_count":3},{"id":"1812.00477","title":"Ego-Downward and Ambient Video based Person Location Association","created":"2018-12-02","cited_by_count":2}],"next_cursor":null}