{"list":"other","total":68,"rows":[{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"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":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"2303.06865","title":"FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU","created":"2023-03-13","cited_by_count":575},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"id":"2202.07800","title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","created":"2022-02-16","cited_by_count":363},{"id":"2005.00200","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","created":"2020-05-01","cited_by_count":362},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361},{"id":"1912.03458","title":"Dynamic Convolution: Attention over Convolution Kernels","created":"2019-12-07","cited_by_count":356},{"id":"1711.09485","title":"SkipNet: Learning Dynamic Routing in Convolutional Networks","created":"2017-11-26","cited_by_count":332},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"2012.00451","title":"Just Ask: Learning to Answer Questions from Millions of Narrated Videos","created":"2020-12-01","cited_by_count":248},{"id":"2012.09852","title":"SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning","created":"2020-12-17","cited_by_count":234},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229},{"id":"2303.16058","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","created":"2023-03-28","cited_by_count":199},{"id":"1711.08393","title":"BlockDrop: Dynamic Inference Paths in Residual Networks","created":"2017-11-22","cited_by_count":189},{"id":"2108.01390","title":"Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer","created":"2021-08-03","cited_by_count":177},{"id":"2112.09583","title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","created":"2021-12-17","cited_by_count":149},{"id":"2205.03436","title":"EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers","created":"2022-05-06","cited_by_count":116},{"id":"2312.10656","title":"VidToMe: Video Token Merging for Zero-Shot Video Editing","created":"2023-12-17","cited_by_count":113},{"id":"2106.05968","title":"Space-time Mixing Attention for Video Transformer","created":"2021-06-10","cited_by_count":84},{"id":"2204.09222","title":"K-LITE: Learning Transferable Visual Models with External Knowledge","created":"2022-04-20","cited_by_count":79},{"id":"2305.17997","title":"DiffRate : Differentiable Compression Rate for Efficient Vision Transformers","created":"2023-05-29","cited_by_count":77},{"id":"2110.03860","title":"Token Pooling in Vision Transformers","created":"2021-10-08","cited_by_count":69},{"id":"1912.01601","title":"LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition","created":"2019-12-03","cited_by_count":65},{"id":"2210.06031","title":"Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning","created":"2022-10-12","cited_by_count":59},{"id":"2204.08412","title":"Temporally Efficient Vision Transformer for Video Instance Segmentation","created":"2022-04-18","cited_by_count":55},{"id":"2311.13160","title":"Large Language Models in Education: Vision and Opportunities","created":"2023-11-22","cited_by_count":54},{"id":"2212.03229","title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning","created":"2022-12-06","cited_by_count":49},{"id":"2310.19060","title":"TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding","created":"2023-10-29","cited_by_count":49},{"id":"1801.03493","title":"Focus: Querying Large Video Datasets with Low Latency and Low Cost","created":"2018-01-10","cited_by_count":46},{"id":"2211.08110","title":"HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers","created":"2022-11-15","cited_by_count":46},{"id":"1612.01669","title":"MarioQA: Answering Questions by Watching Gameplay Videos","created":"2016-12-06","cited_by_count":42},{"id":"1805.01046","title":"BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics","created":"2018-05-02","cited_by_count":41},{"id":"2403.13347","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","created":"2024-03-20","cited_by_count":41},{"id":"2010.13302","title":"AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild","created":"2020-10-26","cited_by_count":40},{"id":"1703.02529","title":"NoScope: Optimizing Neural Network Queries over Video at Scale","created":"2017-03-07","cited_by_count":37},{"id":"2208.08352","title":"FCN-Transformer Feature Fusion for Polyp Segmentation","created":"2022-08-17","cited_by_count":37},{"id":"1912.01046","title":"TutorialVQA: Question Answering Dataset for Tutorial Videos","created":"2019-12-02","cited_by_count":20},{"id":"2203.03996","title":"DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos","created":"2022-03-08","cited_by_count":18},{"id":"1803.06312","title":"EVA$^2$: Exploiting Temporal Redundancy in Live Computer Vision","created":"2018-03-16","cited_by_count":13},{"id":"2308.13494","title":"Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers","created":"2023-08-25","cited_by_count":13},{"id":"2008.06880","title":"Poet: Product-oriented Video Captioner for E-commerce","created":"2020-08-16","cited_by_count":12},{"id":"2009.04540","title":"Semantic Indexes for Machine Learning-based Queries over Unstructured Data","created":"2020-09-09","cited_by_count":11},{"id":"2106.15315","title":"Boggart: Towards General-Purpose Acceleration of Retrospective Video Analytics","created":"2021-06-21","cited_by_count":10},{"id":"1810.01794","title":"VStore: A Data Store for Analytics on Large Videos","created":"2018-10-03","cited_by_count":9},{"id":"2204.03227","title":"Accelerating Attention through Gradient-Based Learned Runtime Pruning","created":"2022-04-07","cited_by_count":8},{"id":"2006.02958","title":"TASM: A Tile-Based Storage Manager for Video Analytics","created":"2020-06-04","cited_by_count":7},{"id":"2207.00588","title":"CoVA: Exploiting Compressed-Domain Analysis to Accelerate Video Analytics","created":"2022-07-02","cited_by_count":6},{"id":"2103.16604","title":"VSS: A Storage System for Video Analytics [Technical Report]","created":"2021-03-30","cited_by_count":5},{"id":"2210.09887","title":"MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videos","created":"2022-10-18","cited_by_count":5},{"id":"2205.03534","title":"Attract me to Buy: Advertisement Copywriting Generation with Multimodal Multi-structured Information","created":"2022-05-07","cited_by_count":3},{"id":"2303.04068","title":"VOCALExplore: Pay-as-You-Go Video Data Exploration and Model Building [Technical Report]","created":"2023-03-07","cited_by_count":2}],"next_cursor":null}