20 results for “spatio-temporal self-attention”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
Shravan Chaudhari, William Paul, Suchi Saria, Rama Chellappa +1 more
This paper presents Ledger, a 3D object memory that builds a persistent memory of objects from egocentric videos.
This paper introduces GazeLNN, a computationally lightweight scanpath prediction model for robot autonomy.
Xiaoyang Jiang, Yanlai Yang, Kenneth A. Norman, Brenden Lake +1 more
The paper introduces BabyCL, a continual multimodal learning framework that processes egocentric video data in a single chronological pass, demonstrating that meaningful word-referent mappings can be…
Like Liu, Zhengzheng Xu, Haitao He, Hongzhe Li +2 more
The paper introduces UAV-DualCog, a benchmark for evaluating multimodal large language models in UAV scenarios for joint self-state and environment-state reasoning.
Zeqi Zheng, Zizheng Zhu, Yuping Yan, Wenxuan Pan +2 more
This paper proposes Spatially Contiguous Local Attention with Boundary Continuity Pathway (SCLA-BCP) for Spiking Transformers, improving spatial locality and consistency across layers and architecture…
The paper introduces Spatially Speculative Decoding, a framework that accelerates autoregressive image generation by up to 13.3x while maintaining high fidelity.
Xiaolin Liu, Yilun Zhu, Xiangyu Zhao, Xuehui Wang +8 more
The paper introduces Moment-Video, a new benchmark that diagnoses the ability of video MLLMs to understand brief, critical visual events, revealing that current models struggle significantly with temp…
Baback Elmieh, Lynn Tsai, Zeman Li, Srinivas Kaza +7 more
The paper proposes a method for online novel view synthesis from multi-view streaming videos, decoupling memory update and application frequencies, using cross-view attention, Memory Loss, and Memory…
Timing Yang, Predrag Neskovic, Jansen Seheult, Wenchao Han +3 more
This paper proposes a self-supervised visual model called RATS that discovers compositional structure in images.
Jingtao He, Hongliang Lu, Xiaoyun Qiu, Yixuan Wang +1 more
The paper introduces a structured multi-level visual perturbation framework to systematically analyze how dependent VLA-based driving behavior is on visual information, revealing uneven visual groundi…
This paper introduces instruction-based vector steering to redistribute attention in Large Audio-Language Models (LALMs) and demonstrates its effectiveness in recovering sound event locations.
Xiao Wang, Minglei Yang, Bin Yang, Wenke Huang +3 more
The paper introduces VIP-Net, a framework that leverages multi-modal spatio-temporal cues and a new dataset (Temporal-VIP) to accurately identify the most influential people in videos, overcoming the…