{"total":87,"rows":[{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613,"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":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328,"area":"ssm"},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320,"area":null},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225,"area":null},{"id":"2201.09450","title":"UniFormer: Unifying Convolution and Self-attention for Visual Recognition","created":"2022-01-24","cited_by_count":206,"area":null},{"id":"2110.03675","title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","created":"2021-10-07","cited_by_count":200,"area":null},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193,"area":null},{"id":"2201.04676","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","created":"2022-01-12","cited_by_count":184,"area":null},{"id":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116,"area":null},{"id":"2203.16761","title":"MeMOT: Multi-Object Tracking with Memory","created":"2022-03-31","cited_by_count":114,"area":null},{"id":"2403.09626","title":"Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding","created":"2024-03-14","cited_by_count":108,"area":"ssm"},{"id":"2107.03377","title":"Long Short-Term Transformer for Online Action Detection","created":"2021-07-07","cited_by_count":88,"area":null},{"id":"2212.05590","title":"PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery","created":"2022-12-11","cited_by_count":87,"area":null},{"id":"2211.01452","title":"MPCFormer: fast, performant and private Transformer inference with MPC","created":"2022-11-02","cited_by_count":69,"area":null},{"id":"2112.01514","title":"Self-supervised Video Transformer","created":"2021-12-02","cited_by_count":64,"area":null},{"id":"2404.16112","title":"Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challenges","created":"2024-04-24","cited_by_count":64,"area":"ssm"},{"id":"2406.10165","title":"CarLLaVA: Vision language models for camera-only closed-loop driving","created":"2024-06-14","cited_by_count":57,"area":"mllm"},{"id":"2305.11019","title":"Annotation-free Audio-Visual Segmentation","created":"2023-05-18","cited_by_count":46,"area":null},{"id":"2106.09212","title":"Long-Short Temporal Contrastive Learning of Video Transformers","created":"2021-06-17","cited_by_count":42,"area":null},{"id":"2302.01738","title":"AIROGS: Artificial Intelligence for RObust Glaucoma Screening Challenge","created":"2023-02-03","cited_by_count":35,"area":null},{"id":"2201.10439","title":"Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Multi-Person Video","created":"2022-01-25","cited_by_count":31,"area":null},{"id":"2205.04749","title":"Spatio-Temporal Transformer for Dynamic Facial Expression Recognition in the Wild","created":"2022-05-10","cited_by_count":29,"area":null},{"id":"2306.08913","title":"Advancing Volumetric Medical Image Segmentation via Global-Local Masked Autoencoder","created":"2023-06-15","cited_by_count":21,"area":null},{"id":"2207.10447","title":"Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration","created":"2022-07-21","cited_by_count":20,"area":null},{"id":"2207.10448","title":"An Efficient Spatio-Temporal Pyramid Transformer for Action Detection","created":"2022-07-21","cited_by_count":16,"area":null},{"id":"2312.01897","title":"Adapting Short-Term Transformers for Action Detection in Untrimmed Videos","created":"2023-12-04","cited_by_count":16,"area":null},{"id":"2301.02642","title":"Triple-stream Deep Metric Learning of Great Ape Behavioural Actions","created":"2023-01-06","cited_by_count":14,"area":null},{"id":"2302.08672","title":"Multimodal Subtask Graph Generation from Instructional Videos","created":"2023-02-17","cited_by_count":13,"area":null},{"id":"2301.02654","title":"Does compressing activations help model parallel training?","created":"2023-01-06","cited_by_count":12,"area":null},{"id":"2207.12842","title":"Unsupervised Domain Adaptation for Video Transformers in Action Recognition","created":"2022-07-26","cited_by_count":10,"area":null},{"id":"2208.03704","title":"Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose Estimation","created":"2022-08-07","cited_by_count":10,"area":null},{"id":"2406.19006","title":"Snakes and Ladders: Two Steps Up for VideoMamba","created":"2024-06-27","cited_by_count":10,"area":"ssm"},{"id":"2505.03798","title":"Position: Foundation Models Need Digital Twin Representations","created":"2025-05-01","cited_by_count":10,"area":null},{"id":"2108.07851","title":"Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Net","created":"2021-08-17","cited_by_count":9,"area":null},{"id":"2210.10039","title":"How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios","created":"2022-10-18","cited_by_count":9,"area":null},{"id":"2207.03800","title":"FastLTS: Non-Autoregressive End-to-End Unconstrained Lip-to-Speech Synthesis","created":"2022-07-08","cited_by_count":8,"area":null},{"id":"2310.15165","title":"Handling Data Heterogeneity via Architectural Design for Federated Visual Recognition","created":"2023-10-23","cited_by_count":8,"area":null},{"id":"2409.00304","title":"StimuVAR: Spatiotemporal Stimuli-aware Video Affective Reasoning with Multimodal Large Language Models","created":"2024-08-31","cited_by_count":8,"area":"lr"},{"id":"2412.02930","title":"TemporalVLM: Video LLMs for Temporal Reasoning in Long Videos","created":"2024-12-04","cited_by_count":8,"area":"lr"},{"id":"2210.08164","title":"Linear Video Transformer with Feature Fixation","created":"2022-10-15","cited_by_count":6,"area":null},{"id":"2301.00230","title":"Disjoint Masking with Joint Distillation for Efficient Masked Image Modeling","created":"2022-12-31","cited_by_count":6,"area":null},{"id":"2109.09536","title":"Audio-Visual Speech Recognition is Worth 32$\\times$32$\\times$8 Voxels","created":"2021-09-20","cited_by_count":5,"area":null},{"id":"2204.00452","title":"Vision Transformer with Cross-attention by Temporal Shift for Efficient Action Recognition","created":"2022-04-01","cited_by_count":5,"area":null},{"id":"2407.06162","title":"RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model","created":"2024-06-02","cited_by_count":5,"area":null},{"id":"2111.09641","title":"Evaluating Transformers for Lightweight Action Recognition","created":"2021-11-18","cited_by_count":4,"area":null},{"id":"2111.13677","title":"SWAT: Spatial Structure Within and Among Tokens","created":"2021-11-26","cited_by_count":4,"area":null},{"id":"2208.14209","title":"A Circular Window-based Cascade Transformer for Online Action Detection","created":"2022-08-30","cited_by_count":4,"area":null},{"id":"2412.10804","title":"Medical Manifestation-Aware De-Identification","created":"2024-12-14","cited_by_count":4,"area":null},{"id":"2602.22571","title":"GIFSplat: Generative Prior-Guided Iterative Feed-Forward 3D Gaussian Splatting from Sparse Views","created":"2026-02-26","cited_by_count":4,"area":null},{"id":"2207.11838","title":"SAVCHOI: Detecting Suspicious Activities using Dense Video Captioning with Human Object Interactions","created":"2022-07-24","cited_by_count":3,"area":null},{"id":"2212.01638","title":"VLG: General Video Recognition with Web Textual Knowledge","created":"2022-12-03","cited_by_count":3,"area":null},{"id":"2410.17098","title":"Activity Recognition on Avatar-Anonymized Datasets with Masked Differential Privacy","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2505.05644","title":"The Moon's Many Faces: A Single Unified Transformer for Multimodal Lunar Reconstruction","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2308.11249","title":"Video BagNet: short temporal receptive fields increase robustness in long-term action recognition","created":"2023-08-22","cited_by_count":2,"area":null},{"id":"2310.14416","title":"ConViViT -- A Deep Neural Network Combining Convolutions and Factorized Self-Attention for Human Activity Recognition","created":"2023-10-22","cited_by_count":2,"area":null},{"id":"2402.14888","title":"Efficient data selection employing Semantic Similarity-based Graph Structures for model training","created":"2024-02-22","cited_by_count":2,"area":null},{"id":"2405.05584","title":"A Survey on Backbones for Deep Video Action Recognition","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2407.19877","title":"Language-driven Grasp Detection with Mask-guided Attention","created":"2024-07-29","cited_by_count":2,"area":null},{"id":"2411.15240","title":"A Foundation Model for Wearable Movement Data in Mental Health Research","created":"2024-11-22","cited_by_count":2,"area":null},{"id":"2501.12632","title":"TeD-Loc: Text Distillation for Weakly Supervised Object Localization","created":"2025-01-22","cited_by_count":2,"area":null},{"id":"2502.19451","title":"Multispectral to Hyperspectral using Pretrained Foundational model","created":"2025-02-26","cited_by_count":2,"area":null},{"id":"2503.08484","title":"Generalizable AI-Generated Image Detection Based on Fractal Self-Similarity in the Spectrum","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2207.03782","title":"VidConv: A modernized 2D ConvNet for Efficient Video Recognition","created":"2022-07-08","cited_by_count":1,"area":null},{"id":"2209.14378","title":"UNesT: Local Spatial Representation Learning with Hierarchical Transformer for Efficient Medical Segmentation","created":"2022-09-28","cited_by_count":1,"area":null},{"id":"2304.02147","title":"ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional Attention","created":"2023-04-04","cited_by_count":1,"area":null},{"id":"2403.08528","title":"Pig aggression classification using CNN, Transformers and Recurrent Networks","created":"2024-03-13","cited_by_count":1,"area":null},{"id":"2404.02562","title":"Representation Alignment Contrastive Regularization for Multi-Object Tracking","created":"2024-04-03","cited_by_count":1,"area":null},{"id":"2407.01375","title":"Transferable-guided Attention Is All You Need for Video Domain Adaptation","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2410.04256","title":"Implicit to Explicit Entropy Regularization: Benchmarking ViT Fine-tuning under Noisy Labels","created":"2024-10-05","cited_by_count":1,"area":null},{"id":"2502.01289","title":"A Framework for Double-Blind Federated Adaptation of Foundation Models","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2502.10682","title":"CAE-Net: Generalized Deepfake Image Detection using Convolution and Attention Mechanisms with Spatial and Frequency Domain Features","created":"2025-02-15","cited_by_count":1,"area":null},{"id":"2504.01386","title":"DALIP: Distribution Alignment-based Language-Image Pre-Training for Domain-Specific Data","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2105.13843","title":"Explainable Enterprise Credit Rating via Deep Feature Crossing Network","created":"2021-05-22","cited_by_count":0,"area":null},{"id":"2109.12499","title":"PETA: Photo Albums Event Recognition using Transformers Attention","created":"2021-09-26","cited_by_count":0,"area":null},{"id":"2304.01236","title":"Astronomical image time series classification using CONVolutional attENTION (ConvEntion)","created":"2023-04-03","cited_by_count":0,"area":null},{"id":"2308.10533","title":"Joint learning of images and videos with a single Vision Transformer","created":"2023-08-21","cited_by_count":0,"area":null},{"id":"2402.18577","title":"Motion Guided Token Compression for Efficient Masked Video Modeling","created":"2024-01-10","cited_by_count":0,"area":"inference"},{"id":"2406.14351","title":"Automatic Labels are as Effective as Manual Labels in Biomedical Images Classification with Deep Learning","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2409.11867","title":"StableMamba: Distillation-free Scaling of Large SSMs for Images and Videos","created":"2024-09-18","cited_by_count":0,"area":"ssm"},{"id":"2411.06363","title":"Layer-Wise Feature Metric of Semantic-Pixel Matching for Few-Shot Learning","created":"2024-11-10","cited_by_count":0,"area":null},{"id":"2502.07277","title":"Enhancing Video Understanding: Deep Neural Networks for Spatiotemporal Analysis","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2503.00348","title":"SHAZAM: Self-Supervised Change Monitoring for Hazard Detection and Mapping","created":"2025-03-01","cited_by_count":0,"area":null},{"id":"2505.19928","title":"CA3D: Convolutional-Attentional 3D Nets for Efficient Video Activity Recognition on the Edge","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2511.20928","title":"Smooth regularization for efficient video recognition","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2602.21064","title":"Motivation is Something You Need","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2608.09276","title":"Verifiably grounded machine interpretation of lunar geology","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":null}