{"list":"other","total":100,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"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":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"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":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"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":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"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":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"2204.04799","title":"DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning","created":"2022-04-10","cited_by_count":642},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"1702.01105","title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","created":"2017-02-03","cited_by_count":406},{"id":"2009.09796","title":"Multi-Task Learning with Deep Neural Networks: A Survey","created":"2020-09-10","cited_by_count":375},{"id":"1910.04751","title":"Panoptic-DeepLab","created":"2019-10-10","cited_by_count":363},{"id":"1706.01427","title":"A simple neural network module for relational reasoning","created":"2017-06-05","cited_by_count":346},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"id":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"2007.04954","title":"ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation","created":"2020-07-09","cited_by_count":250},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189},{"id":"2201.04676","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","created":"2022-01-12","cited_by_count":184},{"id":"1911.12423","title":"AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning","created":"2019-11-27","cited_by_count":160},{"id":"1905.13211","title":"What Can Neural Networks Reason About?","created":"2019-05-30","cited_by_count":159},{"id":"2001.06902","title":"MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning","created":"2020-01-19","cited_by_count":157},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146},{"id":"1801.08297","title":"NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction","created":"2018-01-25","cited_by_count":127},{"id":"2003.08040","title":"Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation","created":"2020-03-18","cited_by_count":126},{"id":"1812.05040","title":"Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach","created":"2018-12-12","cited_by_count":119},{"id":"2008.11714","title":"DRG: Dual Relation Graph for Human-Object Interaction Detection","created":"2020-08-26","cited_by_count":117},{"id":"1902.03748","title":"Peeking into the Future: Predicting Future Person Activities and Locations in Videos","created":"2019-02-11","cited_by_count":114},{"id":"1912.09930","title":"Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks","created":"2019-12-20","cited_by_count":114},{"id":"2001.04583","title":"EGO-TOPO: Environment Affordances from Egocentric Video","created":"2020-01-14","cited_by_count":111},{"id":"1904.01886","title":"DADA: Depth-aware Domain Adaptation in Semantic Segmentation","created":"2019-04-03","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":"1810.10093","title":"Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data","created":"2018-10-23","cited_by_count":94},{"id":"1807.10982","title":"Actor-Centric Relation Network","created":"2018-07-28","cited_by_count":87},{"id":"1705.01861","title":"Action Tubelet Detector for Spatio-Temporal Action Localization","created":"2017-05-04","cited_by_count":77},{"id":"1704.02895","title":"ActionVLAD: Learning spatio-temporal aggregation for action classification","created":"2017-04-10","cited_by_count":73},{"id":"1806.01830","title":"Relational Deep Reinforcement Learning","created":"2018-06-05","cited_by_count":73},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73},{"id":"2104.09496","title":"Temporal Query Networks for Fine-grained Video Understanding","created":"2021-04-19","cited_by_count":68},{"id":"1806.06157","title":"Object Level Visual Reasoning in Videos","created":"2018-06-16","cited_by_count":67},{"id":"1912.07414","title":"Learning Canonical Representations for Scene Graph to Image Generation","created":"2019-12-16","cited_by_count":60},{"id":"2104.00969","title":"TubeR: Tubelet Transformer for Video Action Detection","created":"2021-04-02","cited_by_count":55},{"id":"2112.02990","title":"4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding","created":"2021-12-06","cited_by_count":54},{"id":"2008.10292","title":"Automated Search for Resource-Efficient Branched Multi-Task Networks","created":"2020-08-24","cited_by_count":51},{"id":"2003.14058","title":"MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning","created":"2020-03-31","cited_by_count":50},{"id":"2205.08303","title":"MulT: An End-to-End Multitask Learning Transformer","created":"2022-05-17","cited_by_count":48},{"id":"1912.04070","title":"Synthetic Humans for Action Recognition from Unseen Viewpoints","created":"2019-12-09","cited_by_count":46},{"id":"1802.05451","title":"Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction","created":"2018-02-15","cited_by_count":44},{"id":"1812.03544","title":"A Structured Model For Action Detection","created":"2018-12-09","cited_by_count":43},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38},{"id":"2006.15327","title":"Compositional Video Synthesis with Action Graphs","created":"2020-06-27","cited_by_count":34},{"id":"2205.14354","title":"Multi-Task Learning with Multi-Query Transformer for Dense Prediction","created":"2022-05-28","cited_by_count":34},{"id":"1612.00881","title":"Procedural Generation of Videos to Train Deep Action Recognition Networks","created":"2016-12-02","cited_by_count":31},{"id":"1803.10362","title":"Referring Relationships","created":"2018-03-28","cited_by_count":29},{"id":"2010.14742","title":"ElderSim: A Synthetic Data Generation Platform for Human Action Recognition in Eldercare Applications","created":"2020-10-28","cited_by_count":29},{"id":"2112.00054","title":"Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Data","created":"2021-11-30","cited_by_count":26},{"id":"1902.10200","title":"Differentiable Scene Graphs","created":"2019-02-26","cited_by_count":16},{"id":"1904.10681","title":"A Large-scale Varying-view RGB-D Action Dataset for Arbitrary-view Human Action Recognition","created":"2019-04-24","cited_by_count":16},{"id":"2009.14558","title":"Learning Object Detection from Captions via Textual Scene Attributes","created":"2020-09-30","cited_by_count":14},{"id":"2204.07061","title":"Egocentric Human-Object Interaction Detection Exploiting Synthetic Data","created":"2022-04-14","cited_by_count":11},{"id":"2012.02109","title":"SAFCAR: Structured Attention Fusion for Compositional Action Recognition","created":"2020-12-03","cited_by_count":4}],"next_cursor":null}