{"total":54,"rows":[{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620,"area":null},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200,"area":null},{"id":"2103.13141","title":"Temporal Context Aggregation Network for Temporal Action Proposal Refinement","created":"2021-03-24","cited_by_count":112,"area":null},{"id":"2301.06267","title":"Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models","created":"2023-01-16","cited_by_count":91,"area":null},{"id":"2105.02968","title":"This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks","created":"2021-05-05","cited_by_count":65,"area":null},{"id":"2301.04944","title":"ViTs for SITS: Vision Transformers for Satellite Image Time Series","created":"2023-01-12","cited_by_count":56,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2112.03596","title":"E$^2$(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition","created":"2021-12-07","cited_by_count":50,"area":null},{"id":"2303.14474","title":"3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition","created":"2023-03-25","cited_by_count":40,"area":null},{"id":"2109.02613","title":"Class Semantics-based Attention for Action Detection","created":"2021-09-06","cited_by_count":36,"area":null},{"id":"2102.07092","title":"Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition","created":"2021-02-14","cited_by_count":31,"area":null},{"id":"2210.10775","title":"TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation","created":"2022-10-19","cited_by_count":25,"area":null},{"id":"2103.08310","title":"EmoNet: A Transfer Learning Framework for Multi-Corpus Speech Emotion Recognition","created":"2021-03-10","cited_by_count":17,"area":null},{"id":"2403.17823","title":"Efficient Image Pre-Training with Siamese Cropped Masked Autoencoders","created":"2024-03-26","cited_by_count":17,"area":null},{"id":"2311.17365","title":"Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoning","created":"2023-11-29","cited_by_count":16,"area":"lr"},{"id":"2203.08897","title":"Gate-Shift-Fuse for Video Action Recognition","created":"2022-03-16","cited_by_count":15,"area":null},{"id":"2204.11167","title":"RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning","created":"2022-04-24","cited_by_count":15,"area":null},{"id":"2101.06636","title":"Coarse Temporal Attention Network (CTA-Net) for Driver's Activity Recognition","created":"2021-01-17","cited_by_count":14,"area":null},{"id":"2110.05216","title":"High-order Tensor Pooling with Attention for Action Recognition","created":"2021-10-11","cited_by_count":14,"area":null},{"id":"2304.05106","title":"Another Vertical View: A Hierarchical Network for Heterogeneous Trajectory Prediction via Spectrums","created":"2023-04-11","cited_by_count":14,"area":null},{"id":"2101.07042","title":"CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition","created":"2021-01-18","cited_by_count":12,"area":null},{"id":"2110.14381","title":"Temporal-attentive Covariance Pooling Networks for Video Recognition","created":"2021-10-27","cited_by_count":11,"area":null},{"id":"2303.14543","title":"Topological Pooling on Graphs","created":"2023-03-25","cited_by_count":9,"area":null},{"id":"2108.00596","title":"GTNet:Guided Transformer Network for Detecting Human-Object Interactions","created":"2021-08-02","cited_by_count":8,"area":null},{"id":"2112.06392","title":"The Overlooked Classifier in Human-Object Interaction Recognition","created":"2021-12-13","cited_by_count":8,"area":null},{"id":"2108.06647","title":"Few-Shot Fine-Grained Action Recognition via Bidirectional Attention and Contrastive Meta-Learning","created":"2021-08-15","cited_by_count":7,"area":null},{"id":"2102.08065","title":"Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries","created":"2021-02-16","cited_by_count":6,"area":null},{"id":"2104.08665","title":"Higher Order Recurrent Space-Time Transformer for Video Action Prediction","created":"2021-04-17","cited_by_count":6,"area":null},{"id":"2203.16928","title":"Neural Architecture Search for Speech Emotion Recognition","created":"2022-03-31","cited_by_count":6,"area":null},{"id":"2102.00565","title":"CyclingNet: Detecting cycling near misses from video streams in complex urban scenes with deep learning","created":"2021-01-31","cited_by_count":5,"area":null},{"id":"2112.05861","title":"A Discriminative Channel Diversification Network for Image Classification","created":"2021-12-10","cited_by_count":4,"area":null},{"id":"2405.06574","title":"Deep video representation learning: a survey","created":"2024-05-10","cited_by_count":4,"area":null},{"id":"2105.03089","title":"Human Object Interaction Detection using Two-Direction Spatial Enhancement and Exclusive Object Prior","created":"2021-05-07","cited_by_count":3,"area":null},{"id":"2107.13083","title":"Is Object Detection Necessary for Human-Object Interaction Recognition?","created":"2021-07-27","cited_by_count":3,"area":null},{"id":"2302.01921","title":"Transformers in Action Recognition: A Review on Temporal Modeling","created":"2022-12-29","cited_by_count":3,"area":null},{"id":"2407.12880","title":"Cross-Modal Augmentation for Few-Shot Multimodal Fake News Detection","created":"2024-07-16","cited_by_count":3,"area":null},{"id":"2111.02064","title":"Event and Activity Recognition in Video Surveillance for Cyber-Physical Systems","created":"2021-11-03","cited_by_count":2,"area":null},{"id":"2310.17010","title":"This Reads Like That: Deep Learning for Interpretable Natural Language Processing","created":"2023-10-25","cited_by_count":2,"area":null},{"id":"2101.00850","title":"Low Light Image Enhancement via Global and Local Context Modeling","created":"2021-01-04","cited_by_count":1,"area":null},{"id":"2104.01110","title":"NAS-TC: Neural Architecture Search on Temporal Convolutions for Complex Action Recognition","created":"2021-03-17","cited_by_count":1,"area":null},{"id":"2110.09819","title":"LSTC: Boosting Atomic Action Detection with Long-Short-Term Context","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2209.10770","title":"Multi-level Adversarial Spatio-temporal Learning for Footstep Pressure based FoG Detection","created":"2022-09-22","cited_by_count":1,"area":null},{"id":"2212.03384","title":"DroneAttention: Sparse Weighted Temporal Attention for Drone-Camera Based Activity Recognition","created":"2022-12-07","cited_by_count":1,"area":null},{"id":"2212.08830","title":"Inductive Attention for Video Action Anticipation","created":"2022-12-17","cited_by_count":1,"area":null},{"id":"2103.10567","title":"CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition","created":"2021-03-18","cited_by_count":0,"area":null},{"id":"2110.15574","title":"ST-ABN: Visual Explanation Taking into Account Spatio-temporal Information for Video Recognition","created":"2021-10-29","cited_by_count":0,"area":null},{"id":"2203.05676","title":"The Overlooked Classifier in Human-Object Interaction Recognition","created":"2022-03-10","cited_by_count":0,"area":null},{"id":"2207.13306","title":"Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition","created":"2022-07-27","cited_by_count":0,"area":null},{"id":"2301.06082","title":"A Survey on Human Action Recognition","created":"2022-12-20","cited_by_count":0,"area":null},{"id":"2303.00138","title":"Texture-Based Input Feature Selection for Action Recognition","created":"2023-02-28","cited_by_count":0,"area":null},{"id":"2403.09749","title":"Towards Diverse Perspective Learning with Selection over Multiple Temporal Poolings","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2606.22935","title":"Hybrid Compression: Integrating Pruning and Quantization for Optimized Neural Networks","created":"2026-06-22","cited_by_count":0,"area":null}],"next_cursor":null}