{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1709.04875","title":"Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting","created":"2017-09-14","cited_by_count":1136},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2003.01251","title":"Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud","created":"2020-03-02","cited_by_count":335},{"id":"1511.05298","title":"Structural-RNN: Deep Learning on Spatio-Temporal Graphs","created":"2015-11-17","cited_by_count":234},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"1909.03252","title":"Graph Convolutional Networks for Temporal Action Localization","created":"2019-09-07","cited_by_count":208},{"id":"1605.08110","title":"Video Summarization with Long Short-term Memory","created":"2016-05-26","cited_by_count":142},{"id":"1507.06550","title":"Human Pose Estimation with Iterative Error Feedback","created":"2015-07-23","cited_by_count":121},{"id":"2001.06891","title":"Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences","created":"2020-01-19","cited_by_count":118},{"id":"1705.02950","title":"Learning non-maximum suppression","created":"2017-05-08","cited_by_count":113},{"id":"2003.13942","title":"Spatio-Temporal Graph for Video Captioning with Knowledge Distillation","created":"2020-03-31","cited_by_count":109},{"id":"2002.11566","title":"Object Relational Graph with Teacher-Recommended Learning for Video Captioning","created":"2020-02-26","cited_by_count":107},{"id":"1801.00054","title":"Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward","created":"2017-12-29","cited_by_count":105},{"id":"2107.00650","title":"CLIP-It! Language-Guided Video Summarization","created":"2021-07-01","cited_by_count":99},{"id":"2004.00277","title":"Graph Structured Network for Image-Text Matching","created":"2020-04-01","cited_by_count":93},{"id":"2007.14690","title":"Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition","created":"2020-07-29","cited_by_count":82},{"id":"2005.08271","title":"A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer","created":"2020-05-17","cited_by_count":76},{"id":"1805.10538","title":"Video Summarization Using Fully Convolutional Sequence Networks","created":"2018-05-26","cited_by_count":71},{"id":"2107.12960","title":"Enriching Local and Global Contexts for Temporal Action Localization","created":"2021-07-27","cited_by_count":64},{"id":"1708.09545","title":"Video Summarization with Attention-Based Encoder-Decoder Networks","created":"2017-08-31","cited_by_count":63},{"id":"1903.11328","title":"Rethinking the Evaluation of Video Summaries","created":"2019-03-27","cited_by_count":62},{"id":"2104.14085","title":"Bridge to Answer: Structure-aware Graph Interaction Network for Video Question Answering","created":"2021-04-29","cited_by_count":56},{"id":"2108.08121","title":"Target Adaptive Context Aggregation for Video Scene Graph Generation","created":"2021-08-18","cited_by_count":52},{"id":"1904.12251","title":"Hierarchical Recurrent Neural Network for Video Summarization","created":"2019-04-28","cited_by_count":44},{"id":"1707.04960","title":"Query-Focused Video Summarization: Dataset, Evaluation, and A Memory Network Based Approach","created":"2017-07-16","cited_by_count":42},{"id":"1805.12174","title":"Video Summarization by Learning from Unpaired Data","created":"2018-05-30","cited_by_count":36},{"id":"1910.12906","title":"STEP: Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaits","created":"2019-10-28","cited_by_count":36},{"id":"2105.04066","title":"Reconstructive Sequence-Graph Network for Video Summarization","created":"2021-05-10","cited_by_count":34},{"id":"2007.08809","title":"SumGraph: Video Summarization via Recursive Graph Modeling","created":"2020-07-17","cited_by_count":32},{"id":"2112.00302","title":"Graph Convolutional Module for Temporal Action Localization in Videos","created":"2021-12-01","cited_by_count":29},{"id":"1607.05177","title":"Query-Focused Extractive Video Summarization","created":"2016-07-18","cited_by_count":26},{"id":"1603.03369","title":"Summary Transfer: Exemplar-based Subset Selection for Video Summarization","created":"2016-03-10","cited_by_count":24},{"id":"1904.08265","title":"Cycle-SUM: Cycle-consistent Adversarial LSTM Networks for Unsupervised Video Summarization","created":"2019-04-17","cited_by_count":24},{"id":"1708.00666","title":"Temporal Dynamic Graph LSTM for Action-driven Video Object Detection","created":"2017-08-02","cited_by_count":23},{"id":"2112.04222","title":"Classification-Then-Grounding: Reformulating Video Scene Graphs as Temporal Bipartite Graphs","created":"2021-12-08","cited_by_count":23},{"id":"2201.02494","title":"Progressive Video Summarization via Multimodal Self-supervised Learning","created":"2022-01-07","cited_by_count":21},{"id":"2109.14834","title":"IntentVizor: Towards Generic Query Guided Interactive Video Summarization","created":"2021-09-30","cited_by_count":18},{"id":"2006.14211","title":"Globally-convergent Iteratively Reweighted Least Squares for Robust Regression Problems","created":"2020-06-25","cited_by_count":15},{"id":"1812.10222","title":"3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification","created":"2018-12-26","cited_by_count":14},{"id":"2112.13478","title":"Video Joint Modelling Based on Hierarchical Transformer for Co-summarization","created":"2021-12-27","cited_by_count":10},{"id":"1406.5824","title":"VideoSET: Video Summary Evaluation through Text","created":"2014-06-23","cited_by_count":8},{"id":"1412.3596","title":"EgoSampling: Fast-Forward and Stereo for Egocentric Videos","created":"2014-12-11","cited_by_count":7},{"id":"2207.01814","title":"Multimodal Frame-Scoring Transformer for Video Summarization","created":"2022-07-05","cited_by_count":4},{"id":"2109.02625","title":"ERA: Entity Relationship Aware Video Summarization with Wasserstein GAN","created":"2021-09-06","cited_by_count":3},{"id":"2003.10151","title":"GeoGraph: Learning graph-based multi-view object detection with geometric cues end-to-end","created":"2020-03-23","cited_by_count":1}],"next_cursor":null}