Image de couverture de livre

Efficiently Disentangling CLIP for Multi-Object Perception

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Rawlekar, Samyak, Cai, Yujun, Wang, Yiwei, Yang, Ming-Hsuan, Ahuja, Narendra
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Finding Distributed Object-Centric Properties in Self-Supervised Transformers
par: Rawlekar, Samyak, et autres
Publié: (2026)

Learning Implicit Representation for Reconstructing Articulated Objects
par: Zhang, Hao, et autres
Publié: (2024)

S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video
par: Zhang, Hao, et autres
Publié: (2024)

Rethinking Prompting Strategies for Multi-Label Recognition with Partial Annotations
par: Rawlekar, Samyak, et autres
Publié: (2024)

Improving Multi-label Recognition using Class Co-Occurrence Probabilities
par: Rawlekar, Samyak, et autres
Publié: (2024)

MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMs
par: Ge, Haonan, et autres
Publié: (2025)

CSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseen
par: Zhang, Hao, et autres
Publié: (2023)

PAS: A Training-Free Stabilizer for Temporal Encoding in Video LLMs
par: Sun, Bowen, et autres
Publié: (2025)

Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding
par: Wu, Hang, et autres
Publié: (2026)

Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models
par: Wang, Zhaochen, et autres
Publié: (2025)

SegDebias: Test-Time Bias Mitigation for ViT-Based CLIP via Segmentation
par: Wu, Fangyu, et autres
Publié: (2025)

PhysRig: Differentiable Physics-Based Skinning and Rigging Framework for Realistic Articulated Object Modeling
par: Zhang, Hao, et autres
Publié: (2025)

SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking
par: Li, Sifan, et autres
Publié: (2025)

Weakly Supervised 3D Object Detection via Multi-Level Visual Guidance
par: Huang, Kuan-Chih, et autres
Publié: (2023)

Ranking-aware adapter for text-driven image ordering with CLIP
par: Yu, Wei-Hsiang, et autres
Publié: (2024)

RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes
par: Li, Fang, et autres
Publié: (2025)

Self-Calibrating 4D Novel View Synthesis from Monocular Videos Using Gaussian Splatting
par: Li, Fang, et autres
Publié: (2024)

PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection
par: Huang, Kuan-Chih, et autres
Publié: (2023)

Cure or Poison? Embedding Instructions Visually Alters Hallucination in Vision-Language Models
par: Wang, Zhaochen, et autres
Publié: (2025)

ChainMPQ: Interleaved Text-Image Reasoning Chains for Mitigating Relation Hallucinations
par: Wu, Yike, et autres
Publié: (2025)

ViewFusion: Structured Spatial Thinking Chains for Multi-View Reasoning
par: Tao, Xingjian, et autres
Publié: (2026)

HENet++: Hybrid Encoding and Multi-task Learning for 3D Perception and End-to-end Autonomous Driving
par: Xia, Zhongyu, et autres
Publié: (2025)

Measuring the (Un)Faithfulness of Concept-Based Explanations
par: Kumar, Shubham, et autres
Publié: (2025)

DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning
par: Wu, Hang, et autres
Publié: (2025)

Learning Disentangled Representation for One-shot Progressive Face Swapping
par: Li, Qi, et autres
Publié: (2022)

Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation
par: Zhang, Hao, et autres
Publié: (2025)

City Navigation in the Wild: Exploring Emergent Navigation from Web-Scale Knowledge in MLLMs
par: Dalal, Dwip, et autres
Publié: (2025)

CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination
par: Yang, Kaicheng, et autres
Publié: (2024)

Physically Aware 360$^\circ$ View Generation from a Single Image using Disentangled Scene Embeddings
par: KV, Karthikeya, et autres
Publié: (2025)

SAMOFT: Robust Multi-Object Tracking via Region and Flow
par: Wang, Yanchao, et autres
Publié: (2026)

Language-driven Description Generation and Common Sense Reasoning for Video Action Recognition
par: Hu, Xiaodan, et autres
Publié: (2025)

Incremental Object Detection with CLIP
par: Huang, Ziyue, et autres
Publié: (2023)

Cognitive Disentanglement for Referring Multi-Object Tracking
par: Liang, Shaofeng, et autres
Publié: (2025)

CAPA: Contribution-Aware Pruning and FFN Approximation for Efficient Large Vision-Language Models
par: Jha, Samyak, et autres
Publié: (2026)

HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Cameras
par: Xia, Zhongyu, et autres
Publié: (2024)

MagicPose4D: Crafting Articulated Models with Appearance and Motion Control
par: Zhang, Hao, et autres
Publié: (2024)

Efficient Video Object Segmentation via Modulated Cross-Attention Memory
par: Shaker, Abdelrahman, et autres
Publié: (2024)

CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding
par: Xiao, Linhui, et autres
Publié: (2023)

CLIP-RD: Relative Distillation for Efficient CLIP Knowledge Distillation
par: Chung, Jeannie, et autres
Publié: (2026)

Piecewise-Linear Manifolds for Deep Metric Learning
par: Bhatnagar, Shubhang, et autres
Publié: (2024)