Melika Filvantorkaman, Mohsen Piri: Robust Pre-Training of Medical Vision-and-Language Models with Domain-Invariant Multi-Modal Masked Reconstruction https://arxiv.org/abs/2602.17689 https://arxiv.org/pdf/2602.17689 https://arxiv.org/html/2602.17689

Iele, Romoli, Molino, Ayll\'on, Ruffini, Soda, Tortora: Probabilistic NDVI Forecasting from Sparse Satellite Time Series and Weather Covariates https://arxiv.org/abs/2602.17683 https://arxiv.org/pdf/2602.17683 https://arxiv.org/html/2602.17683

Cheng cheng, Chenxing Wang, Aolin Li, Haijun Wu, Huiyun Hu, Juyuan Wang: When & How to Write for Personalized Demand-aware Query Rewriting in Video Search https://arxiv.org/abs/2602.17667 https://arxiv.org/pdf/2602.17667 https://arxiv.org/html/2602.17667

Vatsal Agarwal, Saksham Suri, Matthew Gwilliam, Pulkit Kumar, Abhinav Shrivastava: Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory https://arxiv.org/abs/2602.18434 https://arxiv.org/pdf/2602.18434 https://arxiv.org/html/2602.18434

Evonne Ng, Siwei Zhang, Zhang Chen, Michael Zollhoefer, Alexander Richard: SARAH: Spatially Aware Real-time Agentic Humans https://arxiv.org/abs/2602.18432 https://arxiv.org/pdf/2602.18432 https://arxiv.org/html/2602.18432

Xia Su, Ruiqi Chen, Benlin Liu, Jingwei Ma, Zonglin Di, Ranjay Krishna, Jon Froehlich: CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigation https://arxiv.org/abs/2602.18424 https://arxiv.org/pdf/2602.18424 https://arxiv.org/html/2602.18424

Linxi Xie, Lisong C. Sun, Ashley Neall, Tong Wu, Shengqu Cai, Gordon Wetzstein: Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control https://arxiv.org/abs/2602.18422 https://arxiv.org/pdf/2602.18422 https://arxiv.org/html/2602.18422

Minh Dinh, St\'ephane Deny: Latent Equivariant Operators for Robust Object Recognition: Promise and Challenges https://arxiv.org/abs/2602.18406 https://arxiv.org/pdf/2602.18406 https://arxiv.org/html/2602.18406

Stefan Becker, Simon Weiss, Wolfgang H\"ubner, Michael Arens: Self-Aware Object Detection via Degradation Manifolds https://arxiv.org/abs/2602.18394 https://arxiv.org/pdf/2602.18394 https://arxiv.org/html/2602.18394

Qingsong Wang, Jiaxing He, Bingzhe Hou, Tieru Wu, Yang Cao, Cailing Yao: G-LoG Bi-filtration for Medical Image Classification https://arxiv.org/abs/2602.18329 https://arxiv.org/pdf/2602.18329 https://arxiv.org/html/2602.18329

Cui, Liu, Dong, Chu, Gu, Yang, Harada: Unifying Color and Lightness Correction with View-Adaptive Curve Adjustment for Robust 3D Novel View Synthesis https://arxiv.org/abs/2602.18322 https://arxiv.org/pdf/2602.18322 https://arxiv.org/html/2602.18322

Tianyi Song, Danail Stoyanov, Evangelos Mazomenos, Francisco Vasconcelos: Diff2DGS: Reliable Reconstruction of Occluded Surgical Scenes via 2D Gaussian Splatting https://arxiv.org/abs/2602.18314 https://arxiv.org/pdf/2602.18314 https://arxiv.org/html/2602.18314

Liu, Talon, Girella, Ruan, Mondo, Bazzani, Wang, Cristani: Multi-Level Conditioning by Pairing Localized Text and Sketch for Fashion Image Generation https://arxiv.org/abs/2602.18309 https://arxiv.org/pdf/2602.18309 https://arxiv.org/html/2602.18309

Shiyan Du, Conghan Yue, Xinyu Cheng, Dongyu Zhang: DEIG: Detail-Enhanced Instance Generation with Fine-Grained Semantic Control https://arxiv.org/abs/2602.18282 https://arxiv.org/pdf/2602.18282 https://arxiv.org/html/2602.18282

Rishika Bhagwatkar, Irina Rish, Nicolas Flammarion, Francesco Croce: On the Adversarial Robustness of Discrete Image Tokenizers https://arxiv.org/abs/2602.18252 https://arxiv.org/pdf/2602.18252 https://arxiv.org/html/2602.18252

Gahyeon Shim, Soogeun Park, Hyemin Ahn: A Self-Supervised Approach on Motion Calibration for Enhancing Physical Plausibility in Text-to-Motion https://arxiv.org/abs/2602.18199 https://arxiv.org/pdf/2602.18199 https://arxiv.org/html/2602.18199

Yang, Liu, Yuan, Song, Ma, Song, Zeng, Sun, Wang, Zhou, Cui, Gong, Zhang: BLM-Guard: Explainable Multimodal Ad Moderation with Chain-of-Thought and Policy-Aligned Rewards https://arxiv.org/abs/2602.18193 https://arxiv.org/pdf/2602.18193 https://arxiv.org/html/2602.18193

Poonam Poonam, Pere-Pau V\'azquez, Timo Ropinski: Evaluating Graphical Perception Capabilities of Vision Transformers https://arxiv.org/abs/2602.18178 https://arxiv.org/pdf/2602.18178 https://arxiv.org/html/2602.18178

Ling Lin, Yang Bai, Heng Su, Congcong Zhu, Yaoxing Wang, Yang Zhou, Huazhu Fu, Jingrun Chen: OODBench: Out-of-Distribution Benchmark for Large Vision-Language Models https://arxiv.org/abs/2602.18094 https://arxiv.org/pdf/2602.18094 https://arxiv.org/html/2602.18094

Hanshuai Cui, Zhiqing Tang, Qianli Ma, Zhi Yao, Weijia Jia: Predict to Skip: Linear Multistep Feature Forecasting for Efficient Diffusion Transformers https://arxiv.org/abs/2602.18093 https://arxiv.org/pdf/2602.18093 https://arxiv.org/html/2602.18093

Kunwar Arpit Singh, Ankush Prakash, Haroon R Lone: DohaScript: A Large-Scale Multi-Writer Dataset for Continuous Handwritten Hindi Text https://arxiv.org/abs/2602.18089 https://arxiv.org/pdf/2602.18089 https://arxiv.org/html/2602.18089

Kontogiorgakis, Askitopoulos, Tsardanidis, Bormpoudakis, Tsoumas, Balampanis, Kontoes: Comparative Assessment of Multimodal Earth Observation Data for Soil Moisture Estimation https://arxiv.org/abs/2602.18083 https://arxiv.org/pdf/2602.18083 https://arxiv.org/html/2602.18083

Daniel Busch, Christian Bohn, Thomas Kurbiel, Klaus Friedrichs, Richard Meyes, Tobias Meisen: Faster Training, Fewer Labels: Self-Supervised Pretraining for Fine-Grained BEV Segmentation https://arxiv.org/abs/2602.18066 https://arxiv.org/pdf/2602.18066 https://arxiv.org/html/2602.18066

Wang, Cai, Low, Liu, Wu, Wang, Wang, Song, Bian, Fu, Jin: 3DMedAgent: Unified Perception-to-Understanding for 3D Medical Analysis https://arxiv.org/abs/2602.18064 https://arxiv.org/pdf/2602.18064 https://arxiv.org/html/2602.18064

Hongsong Wang, Wenjing Yan, Qiuxia Lai, Xin Geng: Temporal Consistency-Aware Text-to-Motion Generation https://arxiv.org/abs/2602.18057 https://arxiv.org/pdf/2602.18057 https://arxiv.org/html/2602.18057

Fu, Zhang, Meng, Tan, Lu, Lu, Wu, Kang, Fong: CityGuard: Graph-Aware Private Descriptors for Bias-Resilient Identity Search Across Urban Cameras https://arxiv.org/abs/2602.18047 https://arxiv.org/pdf/2602.18047 https://arxiv.org/html/2602.18047

Hongyu Qu, Xiangbo Shu, Rui Yan, Hailiang Gao, Wenguan Wang, Jinhui Tang: Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition https://arxiv.org/abs/2602.18043 https://arxiv.org/pdf/2602.18043 https://arxiv.org/html/2602.18043

Guandong Li, Mengxia Ye: Dual-Channel Attention Guidance for Training-Free Image Editing Control in Diffusion Transformers https://arxiv.org/abs/2602.18022 https://arxiv.org/pdf/2602.18022 https://arxiv.org/html/2602.18022

Yang, Chen, Xu, Li, Wu, Wen, Fang, Yu, Zhang, Li, Wang, Liu, Liu, Huang, Wang: UAOR: Uncertainty-aware Observation Reinjection for Vision-Language-Action Models https://arxiv.org/abs/2602.18020 https://arxiv.org/pdf/2602.18020 https://arxiv.org/html/2602.18020

Yujie Jin, Wenxin Zhang, Jingjing Wang, Guodong Zhou: DeepSVU: Towards In-depth Security-oriented Video Understanding via Unified Physical-world Regularized MoE https://arxiv.org/abs/2602.18019 https://arxiv.org/pdf/2602.18019 https://arxiv.org/html/2602.18019

Jiamin Luo, Xuqian Gu, Jingjing Wang, Jiahong Lu: Towards LLM-centric Affective Visual Customization via Efficient and Precise Emotion Manipulating https://arxiv.org/abs/2602.18016 https://arxiv.org/pdf/2602.18016 https://arxiv.org/html/2602.18016

Bakht, Alansari, Din, Naseer, Javed, Hussain, Matas, Mahmood: MUOT_3M: A 3 Million Frame Multimodal Underwater Benchmark and the MUTrack Tracking Method https://arxiv.org/abs/2602.18006 https://arxiv.org/pdf/2602.18006 https://arxiv.org/html/2602.18006

Lan, Zhou, Wei, Yan, Huang, Pu, Luo, Jia: Image Quality Assessment: Exploring Quality Awareness via Memory-driven Distortion Patterns Matching https://arxiv.org/abs/2602.18000 https://arxiv.org/pdf/2602.18000 https://arxiv.org/html/2602.18000

Sun, Du, Feng, Luo, Ding, Shen, Wang, He, Li: ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models https://arxiv.org/abs/2602.17951 https://arxiv.org/pdf/2602.17951 https://arxiv.org/html/2602.17951

Athanasios Angelakis: ZACH-ViT: Regime-Dependent Inductive Bias in Compact Vision Transformers for Medical Imaging https://arxiv.org/abs/2602.17929 https://arxiv.org/pdf/2602.17929 https://arxiv.org/html/2602.17929

Amirhosein Javadi, Chi-Shiang Gau, Konstantinos D. Polyzos, Tara Javidi: A Single Image and Multimodality Is All You Need for Novel View Synthesis https://arxiv.org/abs/2602.17909 https://arxiv.org/pdf/2602.17909 https://arxiv.org/html/2602.17909

Dhruba Ghosh, Yuhui Zhang, Ludwig Schmidt: Understanding the Fine-Grained Knowledge Capabilities of Vision-Language Models https://arxiv.org/abs/2602.17871 https://arxiv.org/pdf/2602.17871 https://arxiv.org/html/2602.17871

Chen, Wang, Zhang, Yi, Zhang, Zou, Cai, Yuan, Li, Yang, Modolo: Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models https://arxiv.org/abs/2602.17869 https://arxiv.org/pdf/2602.17869 https://arxiv.org/html/2602.17869

Domonkos Varga: On the Evaluation Protocol of Gesture Recognition for UAV-based Rescue Operation based on Deep Learning: A Subject-Independence Perspective https://arxiv.org/abs/2602.17854 https://arxiv.org/pdf/2602.17854 https://arxiv.org/html/2602.17854

Adrian Catalin Lutu, Eduard Poesina, Radu Tudor Ionescu: VQPP: Video Query Performance Prediction Benchmark https://arxiv.org/abs/2602.17814 https://arxiv.org/pdf/2602.17814 https://arxiv.org/html/2602.17814

Narges Norouzi, Idil Esen Zulfikar, Niccol`o Cavagnero, Tommie Kerssies, Bastian Leibe, Gijs Dubbelman, Daan de Geus: VidEoMT: Your ViT is Secretly Also a Video Segmentation Model https://arxiv.org/abs/2602.17807 https://arxiv.org/pdf/2602.17807 https://arxiv.org/html/2602.17807

Jose Sosa, Danila Rukhovich, Anis Kacem, Djamila Aouada: Enabling Training-Free Text-Based Remote Sensing Segmentation https://arxiv.org/abs/2602.17799 https://arxiv.org/pdf/2602.17799 https://arxiv.org/html/2602.17799

Peide Zhu, Linbin Lu, Zhiqin Chen, Xiong Chen: LGD-Net: Latent-Guided Dual-Stream Network for HER2 Scoring with Task-Specific Domain Knowledge https://arxiv.org/abs/2602.17793 https://arxiv.org/pdf/2602.17793 https://arxiv.org/html/2602.17793

Xinwei Ju, Rema Daher, Danail Stoyanov, Sophia Bano, Francisco Vasconcelos: Multi-Modal Monocular Endoscopic Depth and Pose Estimation with Edge-Guided Self-Supervision https://arxiv.org/abs/2602.17785 https://arxiv.org/pdf/2602.17785 https://arxiv.org/html/2602.17785

Thambiraja, Taheri, Danecek, Becherini, Pons-Moll, Thies: CLUTCH: Contextualized Language model for Unlocking Text-Conditioned Hand motion modelling in the wild https://arxiv.org/abs/2602.17770 https://arxiv.org/pdf/2602.17770 https://arxiv.org/html/2602.17770

Boda Lin, Yongjie Zhu, Xiaocheng Gong, Wenyu Qin, Meng Wang: KPM-Bench: A Kinematic Parsing Motion Benchmark for Fine-grained Motion-centric Video Understanding https://arxiv.org/abs/2602.17768 https://arxiv.org/pdf/2602.17768 https://arxiv.org/html/2602.17768

[2026-02-23 Mon (UTC), 43 new articles found for csCV Computer Vision and Pattern Recognition]

Varun Burde, Pavel Burget, Torsten Sattler: Benchmarking the Effects of Object Pose Estimation and Reconstruction on Robotic Grasping Success https://arxiv.org/abs/2602.17101 https://arxiv.org/pdf/2602.17101 https://arxiv.org/html/2602.17101

Akira Sakai, Yuma Ichikawa: Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression https://arxiv.org/abs/2602.17063 https://arxiv.org/pdf/2602.17063 https://arxiv.org/html/2602.17063

Iman Ahmadi, Mehrshad Taji, Arad Mahdinezhad Kashani, AmirHossein Jadidi, Saina Kashani, Babak Khalaj: MALLVI: a multi agent framework for integrated generalized robotics manipulation https://arxiv.org/abs/2602.16898 https://arxiv.org/pdf/2602.16898 https://arxiv.org/html/2602.16898