{"total":232,"rows":[{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021,"area":"inference"},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776,"area":"lr"},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330,"area":null},{"id":"2307.04767","title":"Semantic-SAM: Segment and Recognize Anything at Any Granularity","created":"2023-07-10","cited_by_count":185,"area":null},{"id":"2312.10032","title":"Osprey: Pixel Understanding with Visual Instruction Tuning","created":"2023-12-15","cited_by_count":159,"area":"mllm"},{"id":"2312.10103","title":"GSVA: Generalized Segmentation via Multimodal Large Language Models","created":"2023-12-15","cited_by_count":154,"area":"mllm"},{"id":"2301.01795","title":"PACO: Parts and Attributes of Common Objects","created":"2023-01-04","cited_by_count":146,"area":null},{"id":"2305.13310","title":"Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching","created":"2023-05-22","cited_by_count":142,"area":null},{"id":"2206.10207","title":"SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders","created":"2022-06-21","cited_by_count":114,"area":null},{"id":"2112.00933","title":"PartImageNet: A Large, High-Quality Dataset of Parts","created":"2021-12-02","cited_by_count":107,"area":null},{"id":"2307.10173","title":"DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering","created":"2023-07-19","cited_by_count":103,"area":null},{"id":"2403.14598","title":"PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model","created":"2024-03-21","cited_by_count":101,"area":"mllm"},{"id":"2409.19603","title":"One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos","created":"2024-09-29","cited_by_count":100,"area":"lr"},{"id":"2203.07997","title":"InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding","created":"2022-03-15","cited_by_count":89,"area":null},{"id":"2103.04379","title":"Repurposing GANs for One-shot Semantic Part Segmentation","created":"2021-03-07","cited_by_count":88,"area":null},{"id":"2306.04356","title":"Fine-Grained Visual Prompting","created":"2023-06-07","cited_by_count":82,"area":"mllm"},{"id":"2104.13874","title":"Exploring Relational Context for Multi-Task Dense Prediction","created":"2021-04-28","cited_by_count":71,"area":null},{"id":"2409.10542","title":"SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation","created":"2024-09-01","cited_by_count":69,"area":"mllm"},{"id":"2207.03434","title":"LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery","created":"2022-07-07","cited_by_count":66,"area":null},{"id":"2406.20076","title":"EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model","created":"2024-06-28","cited_by_count":65,"area":"mllm"},{"id":"2412.04455","title":"Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection","created":"2024-12-05","cited_by_count":63,"area":null},{"id":"2305.18203","title":"Concept Decomposition for Visual Exploration and Inspiration","created":"2023-05-29","cited_by_count":61,"area":null},{"id":"2207.03337","title":"Factorizing Knowledge in Neural Networks","created":"2022-07-04","cited_by_count":59,"area":null},{"id":"2403.17749","title":"Multi-Task Dense Prediction via Mixture of Low-Rank Experts","created":"2024-03-26","cited_by_count":58,"area":"moe"},{"id":"2111.06349","title":"Unsupervised Part Discovery from Contrastive Reconstruction","created":"2021-11-11","cited_by_count":57,"area":null},{"id":"2106.06351","title":"Part-aware Panoptic Segmentation","created":"2021-06-11","cited_by_count":56,"area":null},{"id":"2203.16421","title":"OPD: Single-view 3D Openable Part Detection","created":"2022-03-30","cited_by_count":54,"area":null},{"id":"2404.18630","title":"4D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic Annotations","created":"2024-04-29","cited_by_count":54,"area":null},{"id":"2408.08862","title":"Visual Agents as Fast and Slow Thinkers","created":"2024-08-16","cited_by_count":53,"area":"lr"},{"id":"2305.11173","title":"Going Denser with Open-Vocabulary Part Segmentation","created":"2023-05-18","cited_by_count":51,"area":null},{"id":"2305.08386","title":"PLIP: Language-Image Pre-training for Person Representation Learning","created":"2023-05-15","cited_by_count":49,"area":null},{"id":"2111.14341","title":"OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images","created":"2021-11-29","cited_by_count":46,"area":null},{"id":"2307.15324","title":"TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts","created":"2023-07-28","cited_by_count":45,"area":"moe"},{"id":"2111.14893","title":"Learning Multiple Dense Prediction Tasks from Partially Annotated Data","created":"2021-11-29","cited_by_count":42,"area":null},{"id":"2410.06964","title":"Bridge the Points: Graph-based Few-shot Segment Anything Semantically","created":"2024-10-09","cited_by_count":35,"area":null},{"id":"2205.14354","title":"Multi-Task Learning with Multi-Query Transformer for Dense Prediction","created":"2022-05-28","cited_by_count":34,"area":null},{"id":"2309.03179","title":"SLiMe: Segment Like Me","created":"2023-09-06","cited_by_count":34,"area":"mllm"},{"id":"2312.17448","title":"Tracking with Human-Intent Reasoning","created":"2023-12-29","cited_by_count":33,"area":"lr"},{"id":"2405.15232","title":"DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception","created":"2024-05-24","cited_by_count":32,"area":"mllm"},{"id":"2212.11042","title":"Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemble","created":"2022-12-21","cited_by_count":31,"area":null},{"id":"2310.05107","title":"OV-PARTS: Towards Open-Vocabulary Part Segmentation","created":"2023-10-08","cited_by_count":31,"area":null},{"id":"2104.11914","title":"EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case","created":"2021-04-24","cited_by_count":30,"area":null},{"id":"2503.13881","title":"MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentation","created":"2025-03-18","cited_by_count":28,"area":"lr"},{"id":"2301.03461","title":"DeMT: Deformable Mixer Transformer for Multi-Task Learning of Dense Prediction","created":"2023-01-09","cited_by_count":27,"area":null},{"id":"2503.01342","title":"UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface","created":"2025-03-03","cited_by_count":27,"area":null},{"id":"2203.13815","title":"Versatile Multi-Modal Pre-Training for Human-Centric Perception","created":"2022-03-25","cited_by_count":26,"area":null},{"id":"2501.08549","title":"The Devil is in Temporal Token: High Quality Video Reasoning Segmentation","created":"2025-01-15","cited_by_count":26,"area":"lr"},{"id":"2404.05673","title":"CoReS: Orchestrating the Dance of Reasoning and Segmentation","created":"2024-04-08","cited_by_count":25,"area":"lr"},{"id":"2306.04619","title":"ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections","created":"2023-06-07","cited_by_count":22,"area":"diffusion"},{"id":"2306.04842","title":"InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding","created":"2023-06-08","cited_by_count":22,"area":null},{"id":"2312.08007","title":"Unveiling Parts Beyond Objects:Towards Finer-Granularity Referring Expression Segmentation","created":"2023-12-13","cited_by_count":22,"area":null},{"id":"2407.02228","title":"MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders","created":"2024-07-02","cited_by_count":22,"area":"ssm"},{"id":"2510.23603","title":"PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity","created":"2025-10-27","cited_by_count":21,"area":"mllm"},{"id":"2108.12828","title":"MEDIC: A Multi-Task Learning Dataset for Disaster Image Classification","created":"2021-08-29","cited_by_count":20,"area":null},{"id":"2203.13909","title":"Concept Embedding Analysis: A Review","created":"2022-03-25","cited_by_count":20,"area":null},{"id":"2312.13783","title":"Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection","created":"2023-12-21","cited_by_count":19,"area":null},{"id":"2212.01806","title":"Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networks","created":"2022-12-04","cited_by_count":18,"area":null},{"id":"2301.00394","title":"Deep Learning Technique for Human Parsing: A Survey and Outlook","created":"2023-01-01","cited_by_count":18,"area":null},{"id":"2309.13556","title":"LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning","created":"2023-09-24","cited_by_count":17,"area":null},{"id":"2103.14098","title":"Learning Part Segmentation through Unsupervised Domain Adaptation from Synthetic Vehicles","created":"2021-03-25","cited_by_count":16,"area":null},{"id":"2106.02523","title":"Hallucination In Object Detection -- A Study In Visual Part Verification","created":"2021-06-04","cited_by_count":16,"area":null},{"id":"2107.04474","title":"Interpretable Compositional Convolutional Neural Networks","created":"2021-07-09","cited_by_count":16,"area":null},{"id":"2310.17914","title":"3D-Aware Visual Question Answering about Parts, Poses and Occlusions","created":"2023-10-27","cited_by_count":16,"area":null},{"id":"2412.11576","title":"DCBM: Data-Efficient Visual Concept Bottleneck Models","created":"2024-12-16","cited_by_count":16,"area":null},{"id":"2305.16804","title":"Towards Open-World Segmentation of Parts","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2407.16696","title":"PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects","created":"2024-07-23","cited_by_count":15,"area":null},{"id":"2306.17465","title":"FedBone: Towards Large-Scale Federated Multi-Task Learning","created":"2023-06-30","cited_by_count":14,"area":null},{"id":"2405.00587","title":"GraCo: Granularity-Controllable Interactive Segmentation","created":"2024-05-01","cited_by_count":13,"area":null},{"id":"2507.19599","title":"Object-centric Video Question Answering with Visual Grounding and Referring","created":"2025-07-25","cited_by_count":13,"area":null},{"id":"2304.03282","title":"Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention","created":"2023-04-06","cited_by_count":12,"area":null},{"id":"2304.10266","title":"OOD-CV-v2: An extended Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images","created":"2023-04-17","cited_by_count":12,"area":null},{"id":"2311.03427","title":"TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene Understanding","created":"2023-11-06","cited_by_count":12,"area":null},{"id":"2505.07209","title":"Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models","created":"2025-05-12","cited_by_count":12,"area":null},{"id":"2505.18816","title":"Reasoning Segmentation for Images and Videos: A Survey","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2101.03919","title":"Comprehensible Convolutional Neural Networks via Guided Concept Learning","created":"2021-01-11","cited_by_count":11,"area":null},{"id":"2105.07065","title":"Visual analogy: Deep learning versus compositional models","created":"2021-05-14","cited_by_count":11,"area":null},{"id":"2209.09117","title":"Part-Based Models Improve Adversarial Robustness","created":"2022-09-15","cited_by_count":11,"area":null},{"id":"2210.09309","title":"RibSeg v2: A Large-scale Benchmark for Rib Labeling and Anatomical Centerline Extraction","created":"2022-10-18","cited_by_count":11,"area":null},{"id":"2304.04140","title":"Semantic Human Parsing via Scalable Semantic Transfer over Multiple Label Domains","created":"2023-04-09","cited_by_count":11,"area":null},{"id":"2306.07404","title":"Compositor: Bottom-up Clustering and Compositing for Robust Part and Object Segmentation","created":"2023-06-12","cited_by_count":11,"area":null},{"id":"2406.10951","title":"Don't Forget Too Much: Towards Machine Unlearning on Feature Level","created":"2024-06-16","cited_by_count":11,"area":"safety"},{"id":"2412.01244","title":"Concept Replacer: Replacing Sensitive Concepts in Diffusion Models via Precision Localization","created":"2024-12-02","cited_by_count":11,"area":"diffusion"},{"id":"2503.10596","title":"GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding","created":"2025-03-13","cited_by_count":11,"area":null},{"id":"2505.14100","title":"Unlocking the Power of SAM 2 for Few-Shot Segmentation","created":"2025-05-20","cited_by_count":11,"area":null},{"id":"2507.22886","title":"Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation","created":"2025-07-30","cited_by_count":11,"area":"lr"},{"id":"2508.00518","title":"Fine-grained Spatiotemporal Grounding on Egocentric Videos","created":"2025-08-01","cited_by_count":11,"area":null},{"id":"2508.14160","title":"RynnEC: Bringing MLLMs into Embodied World","created":"2025-08-19","cited_by_count":11,"area":"mllm"},{"id":"2107.01877","title":"Faster-LTN: a neuro-symbolic, end-to-end object detection architecture","created":"2021-07-05","cited_by_count":10,"area":null},{"id":"2204.05393","title":"Improving Few-Shot Part Segmentation using Coarse Supervision","created":"2022-04-11","cited_by_count":10,"area":null},{"id":"2402.03311","title":"HASSOD: Hierarchical Adaptive Self-Supervised Object Detection","created":"2024-02-05","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":"2504.09480","title":"Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation","created":"2025-04-13","cited_by_count":10,"area":"mllm"},{"id":"2202.10201","title":"OG-SGG: Ontology-Guided Scene Graph Generation. A Case Study in Transfer Learning for Telepresence Robotics","created":"2022-02-21","cited_by_count":9,"area":null},{"id":"2203.16168","title":"FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsing","created":"2022-03-30","cited_by_count":9,"area":null},{"id":"2211.07955","title":"IntegratedPIFu: Integrated Pixel Aligned Implicit Function for Single-view Human Reconstruction","created":"2022-11-15","cited_by_count":9,"area":null},{"id":"2303.11923","title":"Performance-aware Approximation of Global Channel Pruning for Multitask CNNs","created":"2023-03-21","cited_by_count":9,"area":null},{"id":"2412.01398","title":"Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description","created":"2024-12-02","cited_by_count":9,"area":null},{"id":"2209.15087","title":"Zero-shot visual reasoning through probabilistic analogical mapping","created":"2022-09-29","cited_by_count":8,"area":"lr"},{"id":"2303.09663","title":"Efficient Computation Sharing for Multi-Task Visual Scene Understanding","created":"2023-03-16","cited_by_count":8,"area":null},{"id":"2305.15734","title":"On the Impact of Knowledge Distillation for Model Interpretability","created":"2023-05-25","cited_by_count":8,"area":"distill"}],"next_cursor":"100"}