{"list":"other","total":63,"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":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"2103.15436","title":"Transformer Tracking","created":"2021-03-29","cited_by_count":412},{"id":"2103.17154","title":"Learning Spatio-Temporal Transformer for Visual Tracking","created":"2021-03-31","cited_by_count":350},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339},{"id":"2203.11991","title":"Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework","created":"2022-03-22","cited_by_count":330},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328},{"id":"2403.06135","title":"MACE: Mass Concept Erasure in Diffusion Models","created":"2024-03-10","cited_by_count":307},{"id":"2003.12565","title":"Probabilistic Regression for Visual Tracking","created":"2020-03-27","cited_by_count":231},{"id":"2307.12493","title":"TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition","created":"2023-07-24","cited_by_count":182},{"id":"1911.12836","title":"Siam R-CNN: Visual Tracking by Re-Detection","created":"2019-11-28","cited_by_count":174},{"id":"2505.17685","title":"FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving","created":"2025-05-23","cited_by_count":166},{"id":"2303.10826","title":"Visual Prompt Multi-Modal Tracking","created":"2023-03-20","cited_by_count":142},{"id":"2103.16556","title":"Learning Target Candidate Association to Keep Track of What Not to Track","created":"2021-03-30","cited_by_count":131},{"id":"2108.05015","title":"VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows","created":"2021-08-11","cited_by_count":129},{"id":"2401.01686","title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","created":"2024-01-03","cited_by_count":129},{"id":"2107.10224","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","created":"2021-07-21","cited_by_count":126},{"id":"1805.08982","title":"RGB-T Object Tracking:Benchmark and Baseline","created":"2018-05-23","cited_by_count":121},{"id":"2404.06564","title":"MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection","created":"2024-04-09","cited_by_count":113},{"id":"2410.18775","title":"Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances","created":"2024-10-24","cited_by_count":110},{"id":"2104.13202","title":"LasHeR: A Large-scale High-diversity Benchmark for RGBT Tracking","created":"2021-04-27","cited_by_count":96},{"id":"2411.19548","title":"ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration","created":"2024-11-29","cited_by_count":89},{"id":"2509.22548","title":"JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation","created":"2025-09-26","cited_by_count":89},{"id":"2106.07477","title":"S$^2$-MLP: Spatial-Shift MLP Architecture for Vision","created":"2021-06-14","cited_by_count":83},{"id":"2403.15360","title":"SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series","created":"2024-03-22","cited_by_count":82},{"id":"2004.00305","title":"High-Performance Long-Term Tracking with Meta-Updater","created":"2020-04-01","cited_by_count":80},{"id":"2309.14611","title":"Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline","created":"2023-09-26","cited_by_count":73},{"id":"2108.13962","title":"DepthTrack : Unveiling the Power of RGBD Tracking","created":"2021-08-31","cited_by_count":67},{"id":"2108.13341","title":"Hire-MLP: Vision MLP via Hierarchical Rearrangement","created":"2021-08-30","cited_by_count":66},{"id":"2311.15851","title":"Single-Model and Any-Modality for Video Object Tracking","created":"2023-11-27","cited_by_count":65},{"id":"2403.09634","title":"OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning","created":"2024-03-14","cited_by_count":65},{"id":"1908.11714","title":"Multi-Modal Fusion for End-to-End RGB-T Tracking","created":"2019-08-30","cited_by_count":63},{"id":"2203.01666","title":"Correlation-Aware Deep Tracking","created":"2022-03-03","cited_by_count":62},{"id":"2308.14103","title":"Towards Unified Token Learning for Vision-Language Tracking","created":"2023-08-27","cited_by_count":62},{"id":"2207.14571","title":"Prompting for Multi-Modal Tracking","created":"2022-07-29","cited_by_count":59},{"id":"2308.03166","title":"Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects","created":"2023-08-06","cited_by_count":56},{"id":"2111.04426","title":"3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds","created":"2021-11-08","cited_by_count":54},{"id":"2007.13143","title":"Challenge-Aware RGBT Tracking","created":"2020-07-26","cited_by_count":53},{"id":"2312.10611","title":"Bi-directional Adapter for Multi-modal Tracking","created":"2023-12-17","cited_by_count":46},{"id":"2401.01724","title":"Lightweight Adaptive Feature De-drifting for Compressed Image Classification","created":"2024-01-03","cited_by_count":46},{"id":"2401.10090","title":"Cross-Modality Perturbation Synergy Attack for Person Re-identification","created":"2024-01-18","cited_by_count":45},{"id":"2403.16002","title":"SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking","created":"2024-03-24","cited_by_count":44},{"id":"2101.08533","title":"Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method","created":"2021-01-21","cited_by_count":42},{"id":"2208.09787","title":"RGBD1K: A Large-scale Dataset and Benchmark for RGB-D Object Tracking","created":"2022-08-21","cited_by_count":42},{"id":"2503.21309","title":"FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval","created":"2025-03-27","cited_by_count":42},{"id":"2011.07188","title":"Duality-Gated Mutual Condition Network for RGBT Tracking","created":"2020-11-14","cited_by_count":35},{"id":"2309.01728","title":"Generative-based Fusion Mechanism for Multi-Modal Tracking","created":"2023-09-04","cited_by_count":33},{"id":"2504.02261","title":"WonderTurbo: Generating Interactive 3D World in 0.72 Seconds","created":"2025-04-03","cited_by_count":32},{"id":"2401.01244","title":"Temporal Adaptive RGBT Tracking with Modality Prompt","created":"2024-01-02","cited_by_count":30},{"id":"2507.20177","title":"Towards Universal Modal Tracking with Online Dense Temporal Token Learning","created":"2025-07-27","cited_by_count":30},{"id":"2201.12083","title":"DynaMixer: A Vision MLP Architecture with Dynamic Mixing","created":"2022-01-28","cited_by_count":28},{"id":"2501.16583","title":"Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image Restoration","created":"2025-01-27","cited_by_count":28},{"id":"2505.19694","title":"Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition","created":"2025-05-26","cited_by_count":17},{"id":"2410.17606","title":"Towards Effective Data-Free Knowledge Distillation via Diverse Diffusion Augmentation","created":"2024-10-23","cited_by_count":13},{"id":"2307.11458","title":"Strip-MLP: Efficient Token Interaction for Vision MLP","created":"2023-07-21","cited_by_count":12},{"id":"2409.18901","title":"Improving Visual Object Tracking through Visual Prompting","created":"2024-09-27","cited_by_count":9},{"id":"2512.19202","title":"Modular Landfill Remediation for AI Grid Resilience","created":"2025-12-22","cited_by_count":1}],"next_cursor":null}