{"total":36,"rows":[{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326,"area":null},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177,"area":null},{"id":"2312.12359","title":"CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation","created":"2023-12-19","cited_by_count":96,"area":null},{"id":"2401.11673","title":"MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo","created":"2024-01-22","cited_by_count":50,"area":null},{"id":"2312.13216","title":"Improving Semantic Correspondence with Viewpoint-Guided Spherical Maps","created":"2023-12-20","cited_by_count":34,"area":null},{"id":"2406.09415","title":"An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels","created":"2024-06-13","cited_by_count":33,"area":null},{"id":"2403.14625","title":"LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT Descriptors","created":"2024-03-21","cited_by_count":27,"area":null},{"id":"2504.12880","title":"Can Masked Autoencoders Also Listen to Birds?","created":"2025-04-17","cited_by_count":26,"area":null},{"id":"2406.09613","title":"ImageNet3D: Towards General-Purpose Object-Level 3D Understanding","created":"2024-06-13","cited_by_count":25,"area":null},{"id":"2401.06960","title":"Transformer for Object Re-Identification: A Survey","created":"2024-01-13","cited_by_count":22,"area":null},{"id":"2311.09215","title":"ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy","created":"2023-11-15","cited_by_count":19,"area":null},{"id":"2402.10093","title":"MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations","created":"2024-02-15","cited_by_count":19,"area":null},{"id":"2411.09702","title":"On the Surprising Effectiveness of Attention Transfer for Vision Transformers","created":"2024-11-14","cited_by_count":17,"area":null},{"id":"2304.10520","title":"Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget","created":"2023-04-20","cited_by_count":15,"area":null},{"id":"2312.01280","title":"Brain Decodes Deep Nets","created":"2023-12-03","cited_by_count":14,"area":null},{"id":"2412.06639","title":"Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers","created":"2024-12-09","cited_by_count":11,"area":null},{"id":"2603.22387","title":"Efficient Universal Perception Encoder","created":"2026-03-23","cited_by_count":10,"area":null},{"id":"2505.05892","title":"Register and [CLS] tokens yield a decoupling of local and global features in large ViTs","created":"2025-05-09","cited_by_count":9,"area":null},{"id":"2412.04680","title":"Superpixel Tokenization for Vision Transformers: Preserving Semantic Integrity in Visual Tokens","created":"2024-12-06","cited_by_count":7,"area":null},{"id":"2404.05603","title":"Self-Explainable Affordance Learning with Embodied Caption","created":"2024-04-08","cited_by_count":4,"area":null},{"id":"2503.07979","title":"Achieving More with Less: Additive Prompt Tuning for Rehearsal-Free Class-Incremental Learning","created":"2025-03-11","cited_by_count":4,"area":null},{"id":"2512.01405","title":"Fantastic Features and Where to Find Them: A Probing Method to combine Features from Multiple Foundation Models","created":"2025-12-01","cited_by_count":3,"area":null},{"id":"2605.07191","title":"Attention Transfer Is Not Universally Effective for Vision Transformers","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2409.13828","title":"ViTGuard: Attention-aware Detection against Adversarial Examples for Vision Transformer","created":"2024-09-20","cited_by_count":2,"area":null},{"id":"2509.15058","title":"Communication Efficient Split Learning of ViTs with Attention-based Double Compression","created":"2025-09-18","cited_by_count":2,"area":null},{"id":"2601.17950","title":"UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders","created":"2026-01-25","cited_by_count":2,"area":null},{"id":"2510.16446","title":"VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2604.06440","title":"Visual prompting reimagined: The power of the Activation Prompts","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2311.10873","title":"Multi-entity Video Transformers for Fine-Grained Video Representation Learning","created":"2023-11-17","cited_by_count":0,"area":null},{"id":"2311.18710","title":"Meta-Prior: Meta learning for Adaptive Inverse Problem Solvers","created":"2023-11-30","cited_by_count":0,"area":null},{"id":"2601.20526","title":"IOTA: Corrective Knowledge-Guided Prompt Learning via Black-White Box Framework","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2605.29691","title":"Unsupervised Semantic Segmentation Facilitates Model Understanding","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.07882","title":"The Cross-Architecture Substrate: A Domain-Transcendent, Calibration-Surviving Geometric Invariant of Modern Vision Encoders","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.31676","title":"REDI: Corpus Aware Patch Ranking for DINOv3 Token Reduction","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2609.01551","title":"What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.36842","title":"Does the VGGT Family Need All Its Layers?","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}