视频大模型

Clockwork Variational Autoencoders

Vaibhav Saxena, Jimmy Ba, Danijar Hafner

专题命中 长视频与时序推理 ：long video(abstract)；分类 cs.CV

Comments 17 pages, 12 figures, 4 tables

ArrowGAN : Learning to Generate Videos by Learning Arrow of Time

Kibeom Hong, Youngjung Uh, Hyeran Byun

专题命中 长视频与时序推理 ：video generation(abstract)；分类 cs.CV

Comments Neurocomputing

Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences

Rosaura G. VidalMata, Walter J. Scheirer, Anna Kukleva, David Cox, Hilde Kuehne

专题命中 长视频与时序推理 ：long video(abstract)；分类 cs.CV

DeepRemaster: Temporal Source-Reference Attention Networks for Comprehensive Video Enhancement

Satoshi Iizuka, Edgar Simo-Serra

专题命中 长视频与时序推理 ：long video(abstract)；分类 cs.CV

Comments Accepted to SIGGRAPH Asia 2019. Project page: http://iizuka.cs.tsukuba.ac.jp/projects/remastering/

Tripping through time: Efficient Localization of Activities in Videos

Meera Hahn, Asim Kadav, James M. Rehg, Hans Peter Graf

专题命中 长视频与时序推理 ：long video(abstract)；分类 cs.CV

Comments Presented at BMVC, 2020

Top-1 Solution of Multi-Moments in Time Challenge 2019

Manyuan Zhang, Hao Shao, Guanglu Song, Yu Liu, Junjie Yan

专题命中 长视频与时序推理 ：video understanding(abstract)；分类 cs.CV

Temporal Interlacing Network

Hao Shao, Shengju Qian, Yu Liu

专题命中 长视频与时序推理 ：video understanding(abstract)；分类 cs.CV

Comments Accepted to AAAI 2020. Winning entry of ICCV Multi-Moments in Time Challenge 2019. Code is available at https://github.com/deepcs233/TIN

BERT for Large-scale Video Segment Classification with Test-time Augmentation

Tianqi Liu, Qizhan Shao

专题命中 长视频与时序推理 ：video understanding(abstract)；分类 cs.CV

Comments ICCV 2019 YouTube8M workshop

Journal ref ICCV 2019

Only Time Can Tell: Discovering Temporal Data for Temporal Modeling

Laura Sevilla-Lara, Shengxin Zha, Zhicheng Yan, Vedanuj Goswami, Matt Feiszli, Lorenzo Torresani

专题命中 长视频与时序推理 ：video understanding(abstract)；分类 cs.CV

VideoGraph: Recognizing Minutes-Long Human Activities in Videos

Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders

专题命中 长视频与时序推理 ：long video(abstract)；分类 cs.CV

Journal ref ICCV 2019, Workshop on Scene Graph Representation and Learning

Model Decay in Long-Term Tracking

Efstratios Gavves, Ran Tao, Deepak K. Gupta, Arnold W. M. Smeulders

专题命中 长视频与时序推理 ：long video(abstract)；分类 cs.CV

Video-based Person Re-identification with Two-stream Convolutional Network and Co-attentive Snippet Embedding

Peixian Chen, Pingyang Dai, Qiong Wu, Yuyu Huang

专题命中 长视频与时序推理 ：long video(abstract)；分类 cs.CV

Comments 5 pages, 2 figures

Mapping Areas using Computer Vision Algorithms and Drones

Bashar Alhafni, Saulo Fernando Guedes, Lays Cavalcante Ribeiro, Juhyun Park, Jeongkyu Lee

专题命中 长视频与时序推理 ：long video(abstract)；分类 cs.CV

Comments 7 pages, 12 figures. This work was presented at the American Society for Engineering Education (ASEE) Northeast Conference in 2016

Future semantic segmentation of time-lapsed videos with large temporal displacement

Talha Siddiqui, Samarth Bharadwaj

专题命中 长视频与时序推理 ：video understanding(abstract)；分类 cs.CV

Comments 12 pages, 7 figures, https://bit.ly/2Bw7HGP

Online Illumination Invariant Moving Object Detection by Generative Neural Network

Fateme Bahri, Moein Shakeri, Nilanjan Ray

专题命中 长视频与时序推理 ：long video(abstract)；分类 cs.CV

Person Search in Videos with One Portrait Through Visual and Temporal Links

Qingqiu Huang, Wentao Liu, Dahua Lin

专题命中 长视频与时序推理 ：long video(abstract)；分类 cs.CV

Comments European Conference on Computer Vision (ECCV), 2018

Video Time: Properties, Encoders and Evaluation

Amir Ghodrati, Efstratios Gavves, Cees G. M. Snoek

专题命中 长视频与时序推理 ：video understanding(abstract)；分类 cs.CV

Comments 14 pages, BMVC 2018

Deep Spatio-Temporal Random Fields for Efficient Video Segmentation

Siddhartha Chandra, Camille Couprie, Iasonas Kokkinos

专题命中 长视频与时序推理 ：video understanding(abstract)；分类 cs.CV

Comments CVPR 2018

When will you do what? - Anticipating Temporal Occurrences of Activities

Yazan Abu Farha, Alexander Richard, Juergen Gall

专题命中 长视频与时序推理 ：long video(abstract)；分类 cs.CV

Comments CVPR 2018

Image Registration Based Flicker Solving in Video Face Replacement and Analysis Based Sub-pixel Image Registration

Xiaofang Wang, Guoqiang Xiang, Xinyue Zhang, Wei Wei

专题命中 长视频与时序推理 ：long video(abstract)；分类 cs.CV

Comments 9 Pages, 10 figures, partly accepted by 2017 Intelligent Computing and Information Systems (ICIS2017)

Probabilistic Global Scale Estimation for MonoSLAM Based on Generic Object Detection

Edgar Sucar, Jean-Bernard Hayet

专题命中 长视频与时序推理 ：long video(abstract)；分类 cs.CV

Comments Int. Workshop on Visual Odometry, CVPR, (July 2017)

Anomaly Detection in Video Using Predictive Convolutional Long Short-Term Memory Networks

Jefferson Ryan Medel, Andreas Savakis

专题命中 长视频与时序推理 ：long video(abstract)；分类 cs.CV

Real-Time Video Highlights for Yahoo Esports

Yale Song

专题命中 长视频与时序推理 ：video understanding(abstract)；分类 cs.CV

Multi-Person Tracking by Multicut and Deep Matching

Siyu Tang, Bjoern Andres, Mykhaylo Andriluka, Bernt Schiele

专题命中 长视频与时序推理 ：long video(abstract)；分类 cs.CV

Visual Tracking via Reliable Memories

Shu Wang, Shaoting Zhang, Wei Liu, Dimitris N. Metaxas

专题命中 长视频与时序推理 ：long video(abstract)；分类 cs.CV

Coreset-Based Adaptive Tracking

Abhimanyu Dubey, Nikhil Naik, Dan Raviv, Rahul Sukthankar, Ramesh Raskar

专题命中 长视频与时序推理 ：long video(abstract)；分类 cs.CV

Comments 8 pages, 5 figures, In submission to IEEE TPAMI (Transactions on Pattern Analysis and Machine Intelligence)

Multiple-object tracking in cluttered and crowded public spaces

Rhys Martin, Ognjen Arandjelović

专题命中 长视频与时序推理 ：long video(abstract)；分类 cs.CV

Journal ref Lecture Notes in Computer Science, volume 6455, pp 89-98, 2010

RRM: Experience-Driven Reflective Retrieval Memory for Long-Horizon Multimodal Reasoning

RRM：用于长周期多模态推理的经验驱动反思式检索记忆

Jingxiang Fan, Junbao Zhuo, Bochao Zou

专题命中 长视频与时序推理 ：long video(abstract)

AI总结 该研究针对现有多模态长期智能体检索机制不足的问题，提出RRM框架，通过反思式经验记忆提炼跨任务检索策略，在多个多模态推理数据集上取得优于现有方法的性能。

AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report

阿莱雅世界：交互式长视野世界建模——完整技术报告

AlayaWorld Team, Kaipeng Zhang, Chuanhao Li, Yifan Zhan, Yongtao Ge, Yuanyang Yin, Jiaming Tan, Kang He, Liaoyuan Fan, Mingliang Zhai, Ruicong Liu, Xiaojie Xu, Xuangeng Chu, Zhen Li, Zhengyuan Lin, Zhixiang Wang, Zian Meng, Zihui Gao

机构 * Alaya Lab（阿莱亚实验室） 纠错

专题命中 长视频与时序推理 ：video diffusion(abstract)

AI总结 研究旨在创建交互式视频世界模型，核心方法是基于15B视频扩散变压器构建阿莱雅世界，通过自回归生成短潜在块等实现多种能力，在iWorld - Bench上长视野生成性能最佳，为相关研究提供开源可扩展基础。

Comments Authors are listed alphabetically by the first name and their role. See the contribution section for details

Spatiotemporal Knowledge Graphs as Persistent Scene Memory for Embodied Question Answering

VL-KnG：从单目视频构建持久时空知识图谱以实现具身场景理解

Mohamad Al Mdfaa, Svetlana Lukina, Timur Akhtyamov, Arthur Nigmatzyanov, Dmitrii Nalberskii, Sergey Zagoruyko, Gonzalo Ferrer

机构 * Applied AI Institute, Moscow, Russia（莫斯科应用人工智能研究所） 纠错

专题命中 长视频与时序推理 ：long video(abstract)

AI总结 VL-KnG通过构建时空知识图谱实现高效具身场景理解，采用LLM驱动的时空对象关联和图增强检索，无需3D重建，支持常数时间推理，优于现有前沿VLMs。