{"total":206,"rows":[{"id":"2303.04671","title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","created":"2023-03-08","cited_by_count":668,"area":"lr"},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565,"area":null},{"id":"2205.04437","title":"Activating More Pixels in Image Super-Resolution Transformer","created":"2022-05-09","cited_by_count":438,"area":null},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321,"area":null},{"id":"2205.14401","title":"Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training","created":"2022-05-28","cited_by_count":264,"area":null},{"id":"2203.04838","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","created":"2022-03-09","cited_by_count":231,"area":null},{"id":"2305.11147","title":"UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild","created":"2023-05-18","cited_by_count":200,"area":"diffusion"},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193,"area":null},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179,"area":null},{"id":"2204.03645","title":"DaViT: Dual Attention Vision Transformers","created":"2022-04-07","cited_by_count":175,"area":null},{"id":"2405.07992","title":"MambaOut: Do We Really Need Mamba for Vision?","created":"2024-05-13","cited_by_count":143,"area":"ssm"},{"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":"2205.03892","title":"ConvMAE: Masked Convolution Meets Masked Autoencoders","created":"2022-05-08","cited_by_count":105,"area":null},{"id":"2305.01115","title":"In-Context Learning Unlocked for Diffusion Models","created":"2023-05-01","cited_by_count":104,"area":"diffusion"},{"id":"2209.14169","title":"CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention","created":"2022-09-28","cited_by_count":103,"area":null},{"id":"2304.03307","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","created":"2023-04-06","cited_by_count":91,"area":null},{"id":"2306.16623","title":"The Segment Anything Model (SAM) for Remote Sensing Applications: From Zero to One Shot","created":"2023-06-29","cited_by_count":83,"area":null},{"id":"2205.14871","title":"You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction","created":"2022-05-30","cited_by_count":81,"area":null},{"id":"2212.04979","title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","created":"2022-12-09","cited_by_count":70,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2309.05239","title":"HAT: Hybrid Attention Transformer for Image Restoration","created":"2023-09-11","cited_by_count":66,"area":null},{"id":"2207.05501","title":"Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios","created":"2022-07-12","cited_by_count":65,"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":"2305.16223","title":"Prompt-Free Diffusion: Taking \"Text\" out of Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":62,"area":"diffusion"},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59,"area":null},{"id":"2306.11249","title":"OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning","created":"2023-06-20","cited_by_count":54,"area":null},{"id":"2211.09529","title":"InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges","created":"2022-11-17","cited_by_count":48,"area":null},{"id":"2304.06446","title":"SpectFormer: Frequency and Attention is what you need in a Vision Transformer","created":"2023-04-13","cited_by_count":48,"area":null},{"id":"2410.11842","title":"MoH: Multi-Head Attention as Mixture-of-Head Attention","created":"2024-10-15","cited_by_count":44,"area":"moe"},{"id":"2205.05675","title":"NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results","created":"2022-05-11","cited_by_count":40,"area":null},{"id":"2404.02132","title":"ViTamin: Designing Scalable Vision Models in the Vision-Language Era","created":"2024-04-02","cited_by_count":39,"area":"mllm"},{"id":"2504.07960","title":"VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning","created":"2025-04-10","cited_by_count":39,"area":"diffusion"},{"id":"2307.08763","title":"Video-Mined Task Graphs for Keystep Recognition in Instructional Videos","created":"2023-07-17","cited_by_count":35,"area":null},{"id":"2302.01791","title":"DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition","created":"2023-02-03","cited_by_count":34,"area":null},{"id":"2309.07911","title":"Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning","created":"2023-09-14","cited_by_count":32,"area":null},{"id":"2209.10218","title":"HiFuse: Hierarchical Multi-Scale Feature Fusion Network for Medical Image Classification","created":"2022-09-21","cited_by_count":30,"area":null},{"id":"2304.02560","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","created":"2023-04-05","cited_by_count":28,"area":"mllm"},{"id":"2204.02148","title":"Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition","created":"2022-04-05","cited_by_count":27,"area":null},{"id":"2206.06801","title":"Peripheral Vision Transformer","created":"2022-06-14","cited_by_count":27,"area":null},{"id":"2206.09325","title":"EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm","created":"2022-06-19","cited_by_count":27,"area":null},{"id":"2309.10356","title":"RoadFormer: Duplex Transformer for RGB-Normal Semantic Road Scene Parsing","created":"2023-09-19","cited_by_count":27,"area":null},{"id":"2502.20087","title":"OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels","created":"2025-02-27","cited_by_count":25,"area":null},{"id":"2302.04542","title":"Efficient Attention via Control Variates","created":"2023-02-09","cited_by_count":23,"area":null},{"id":"2410.10604","title":"Multi-modal Vision Pre-training for Medical Image Analysis","created":"2024-10-14","cited_by_count":23,"area":null},{"id":"2412.14719","title":"Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition","created":"2024-12-19","cited_by_count":22,"area":null},{"id":"2310.19380","title":"TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition","created":"2023-10-30","cited_by_count":21,"area":null},{"id":"2402.08506","title":"P-Mamba: Marrying Perona Malik Diffusion with Mamba for Efficient Pediatric Echocardiographic Left Ventricular Segmentation","created":"2024-02-13","cited_by_count":21,"area":"ssm"},{"id":"2404.17433","title":"PromptCIR: Blind Compressed Image Restoration with Prompt Learning","created":"2024-04-26","cited_by_count":20,"area":null},{"id":"2306.06635","title":"2-D SSM: A General Spatial Layer for Visual Transformers","created":"2023-06-11","cited_by_count":18,"area":null},{"id":"2202.13393","title":"TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation","created":"2022-02-27","cited_by_count":17,"area":"distill"},{"id":"2311.01310","title":"Scattering Vision Transformer: Spectral Mixing Matters","created":"2023-11-02","cited_by_count":17,"area":null},{"id":"2402.17246","title":"SDR-Former: A Siamese Dual-Resolution Transformer for Liver Lesion Classification Using 3D Multi-Phase Imaging","created":"2024-02-27","cited_by_count":17,"area":null},{"id":"2210.05960","title":"Efficient Image Super-Resolution using Vast-Receptive-Field Attention","created":"2022-10-12","cited_by_count":16,"area":null},{"id":"2404.09432","title":"The 8th AI City Challenge","created":"2024-04-15","cited_by_count":16,"area":null},{"id":"2301.07944","title":"Revisiting the Spatial and Temporal Modeling for Few-shot Action Recognition","created":"2023-01-19","cited_by_count":15,"area":null},{"id":"2404.03924","title":"Learning Correlation Structures for Vision Transformers","created":"2024-04-05","cited_by_count":15,"area":null},{"id":"2303.12149","title":"SPARTAN: Self-supervised Spatiotemporal Transformers Approach to Group Activity Recognition","created":"2023-03-06","cited_by_count":14,"area":null},{"id":"2408.06158","title":"OmniCLIP: Adapting CLIP for Video Recognition with Spatial-Temporal Omni-Scale Feature Learning","created":"2024-08-12","cited_by_count":14,"area":"mllm"},{"id":"2409.09649","title":"SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks","created":"2024-09-15","cited_by_count":14,"area":"ssm"},{"id":"2405.18425","title":"ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention","created":"2024-05-28","cited_by_count":13,"area":null},{"id":"2303.05475","title":"Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimicking","created":"2023-03-09","cited_by_count":12,"area":null},{"id":"2303.09756","title":"Video Action Recognition with Attentive Semantic Units","created":"2023-03-17","cited_by_count":12,"area":"mllm"},{"id":"2304.03282","title":"Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention","created":"2023-04-06","cited_by_count":12,"area":null},{"id":"2311.15619","title":"Align before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition","created":"2023-11-27","cited_by_count":12,"area":null},{"id":"2402.02046","title":"TCI-Former: Thermal Conduction-Inspired Transformer for Infrared Small Target Detection","created":"2024-02-03","cited_by_count":12,"area":null},{"id":"2311.15157","title":"Advancing Vision Transformers with Group-Mix Attention","created":"2023-11-26","cited_by_count":11,"area":null},{"id":"2403.16143","title":"CFAT: Unleashing TriangularWindows for Image Super-resolution","created":"2024-03-24","cited_by_count":11,"area":null},{"id":"2408.11481","title":"VE-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment","created":"2024-08-21","cited_by_count":11,"area":"alignment"},{"id":"2304.13009","title":"The Potential of Visual ChatGPT For Remote Sensing","created":"2023-04-25","cited_by_count":10,"area":null},{"id":"2403.08330","title":"Activating Wider Areas in Image Super-Resolution","created":"2024-03-13","cited_by_count":10,"area":null},{"id":"2404.03527","title":"HAPNet: Toward Superior RGB-Thermal Scene Parsing via Hybrid, Asymmetric, and Progressive Heterogeneous Feature Fusion","created":"2024-04-04","cited_by_count":10,"area":null},{"id":"2408.03500","title":"e-Health CSIRO at RRG24: Entropy-Augmented Self-Critical Sequence Training for Radiology Report Generation","created":"2024-08-07","cited_by_count":10,"area":null},{"id":"2408.15101","title":"MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoders","created":"2024-08-27","cited_by_count":10,"area":"ssm"},{"id":"2504.20041","title":"Learning Streaming Video Representation via Multitask Training","created":"2025-04-28","cited_by_count":10,"area":null},{"id":"2409.16652","title":"Progressive Representation Learning for Real-Time UAV Tracking","created":"2024-09-25","cited_by_count":9,"area":null},{"id":"2412.00932","title":"FIction: 4D Future Interaction Prediction from Video","created":"2024-12-01","cited_by_count":9,"area":null},{"id":"2305.06310","title":"SoGAR: Self-supervised Spatiotemporal Attention-based Social Group Activity Recognition","created":"2023-04-27","cited_by_count":8,"area":null},{"id":"2406.13181","title":"The Impact of Auxiliary Patient Data on Automated Chest X-Ray Report Generation and How to Incorporate It","created":"2024-06-19","cited_by_count":8,"area":null},{"id":"2206.11073","title":"A Unified and Biologically-Plausible Relational Graph Representation of Vision Transformers","created":"2022-05-20","cited_by_count":7,"area":null},{"id":"2211.14557","title":"CMC v2: Towards More Accurate COVID-19 Detection with Discriminative Video Priors","created":"2022-11-26","cited_by_count":7,"area":null},{"id":"2310.18698","title":"Triplet Attention Transformer for Spatiotemporal Predictive Learning","created":"2023-10-28","cited_by_count":7,"area":null},{"id":"2312.05803","title":"Transformer-based Selective Super-Resolution for Efficient Image Refinement","created":"2023-12-10","cited_by_count":7,"area":null},{"id":"2401.00722","title":"BRAU-Net++: U-Shaped Hybrid CNN-Transformer Network for Medical Image Segmentation","created":"2024-01-01","cited_by_count":7,"area":null},{"id":"2401.01823","title":"Detours for Navigating Instructional Videos","created":"2024-01-03","cited_by_count":7,"area":null},{"id":"2401.07942","title":"Transformer-based Video Saliency Prediction with High Temporal Dimension Decoding","created":"2024-01-15","cited_by_count":7,"area":null},{"id":"2405.11180","title":"GestFormer: Multiscale Wavelet Pooling Transformer Network for Dynamic Hand Gesture Recognition","created":"2024-05-18","cited_by_count":7,"area":null},{"id":"2406.09390","title":"LLAVIDAL: A Large LAnguage VIsion Model for Daily Activities of Living","created":"2024-06-13","cited_by_count":7,"area":null},{"id":"2208.03062","title":"Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection","created":"2022-08-05","cited_by_count":6,"area":null},{"id":"2302.08374","title":"Efficiency 360: Efficient Vision Transformers","created":"2023-02-16","cited_by_count":6,"area":null},{"id":"2402.08875","title":"Advancing Human Action Recognition with Foundation Models trained on Unlabeled Public Videos","created":"2024-02-14","cited_by_count":6,"area":null},{"id":"2402.18951","title":"Percept, Chat, and then Adapt: Multimodal Knowledge Transfer of Foundation Models for Open-World Video Recognition","created":"2024-02-29","cited_by_count":6,"area":null},{"id":"2412.04786","title":"Slicing Vision Transformer for Flexible Inference","created":"2024-12-06","cited_by_count":6,"area":null},{"id":"2505.19985","title":"Structured Initialization for Vision Transformers","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2312.00188","title":"REACT: Recognize Every Action Everywhere All At Once","created":"2023-11-27","cited_by_count":5,"area":null},{"id":"2410.10497","title":"Continual Learning Improves Zero-Shot Action Recognition","created":"2024-10-14","cited_by_count":5,"area":null},{"id":"2401.12511","title":"Convolutional Initialization for Data-Efficient Vision Transformers","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2404.01139","title":"Structured Initialization for Attention in Vision Transformers","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2410.12342","title":"Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation","created":"2024-10-16","cited_by_count":4,"area":"distill"},{"id":"2410.20348","title":"UTSRMorph: A Unified Transformer and Superresolution Network for Unsupervised Medical Image Registration","created":"2024-10-27","cited_by_count":4,"area":null},{"id":"2411.14927","title":"LiDAR-based End-to-end Temporal Perception for Vehicle-Infrastructure Cooperation","created":"2024-11-22","cited_by_count":4,"area":null}],"next_cursor":"100"}