Cog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and Understanding

Cog-VADU reformulates video anomaly detection as sequential cognitive reasoning via recurrent chain-of-thought prompting and cross-modal re-ranking for training-free zero-shot performance.

Mohd Ubaid Wani, Sara Atito, Josef Kittler, Muhammad Awais

Published Oct 1, 2026 · 0 citations

A comprehensive survey on RGB-D-based human action recognition: algorithms, datasets, and popular applications

This survey reviews CNN, RNN, and Transformer algorithms, datasets, and applications for RGB-D human action recognition.

Yumin Zhang, Yanyong Wang

Published Aug 13, 2025 · 16 citations

Adaptive Residual Quantization for Memory-Efficient Temporal Action Segmentation

Gerard L Donahue, Guven Gergerli, Ayush Gupta, Reza Ghoddoosian and 2 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

A Principled Optimal Transport Framework for Frame Selection in Long Video Understanding

Ziwei Zhao, Yuhang Liu

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

StreamMind: Dynamic Streaming Cognition for Online Video Understanding

Zhuojie Wu, Xin Shen, Chenxi Miao, Weikang Li and 3 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Does Inference-Time Reasoning Really Improve Video Understanding?

Zhuohao Yu, Yu Zhou, Zhecan Wang, Rui Sun and 2 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Towards Generalizable Partially Relevant Video Retrieval

Woojin Jun, Cheol-Ho Cho, MinSeok Jung, SuBeen Lee and 1 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Emotion-Trained Vision Models Do Not Necessarily Learn EEG-Aligned Facial Dynamics

Maryem Benslimane, Hamza Abdelhedi, Vanessa Hadid, Karim Jerbi

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

TTVidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining

Shih-Ying Yeh, Daniel Z Kaplan, Xuehai Wang, Fu-En Yang and 2 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

LifeStream: Token Life-Cycle Modeling for Training-Free Online Video Understanding

Yifan Ge, Zhihang Liu, Jiannan Ge, Chenhui Jin and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Long-Term Composition of Human-Object Interactions

Dayoung Gong, Minsu Cho, Gul Varol

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Temporal Slice Learning for AI-Generated Video Detection with 400× Fewer FLOPs

Wei Shang, Zhiyuan Li, Shengfeng He

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

FrameScout: Scouting Query-Relevant Frames for Long Video Understanding

Haonan Hu, Shuhao Chen, Weisen Jiang, Lizhao Gao and 2 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

TimeTraveler: Temporal Strategy Planning with Time Dictionary for Streaming Video Understanding

Minkuk Kim, Junho Kim, Seong Tae Kim

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Reinforced Evidence-Aware Long Video Understanding

Yuan Xie, Tianshui Chen, Deyu Zhou, Lionel Ni

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

AuGhostmentation: The Eyes Never Stand Still—$\textit{Why Should CNNs?}$

Emirhan Inan, Suayb Arslan

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

TRACE: Trajectory-Aware Conceps for Explainable Video Understanding

Wooil Lee, Junpyo Hong, Jongseo Lee, Tuomas Oikarinen and 2 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

WayPOP: A Panoramic Open-Set Panoptic Tracking Benchmark

Rohit Mohan, Maximilian Luz, Swarnava Chowdhury, Yao Lu and 6 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

SEEK-VAU: Towards Evidence-Faithful Video Anomaly Understanding via Agentic Search

MINGHE WANG, Weijun Zeng, Dapeng Luo, Xinyue Wang and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

StaDy: Factorizing the World into Static and Dynamic via Likelihood Matching

Thomas Ressler-Antal, Frank Fundel, Malek Ben Alaya, Stefan Andreas Baumann and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Hierarchical Adaptive Frame Sampling For Video Understanding

Y Ys, Daiqi Shi, Shuang Li, Liao Zhang and 2 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

HIMMEL: Hierarchical Interleaved Multi-stream Motion Encoding for Long Video Understanding

Haopeng Jin, Tiankun Yang, Zhenyu Guan, ShiQuan Dong and 6 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Isharah-Selfie: Continuous Sign Language Recognition Dataset for One-handed Signing

Ahmed A Hasanaath, Murtadha Aljubran, Sarah Alyami, Muhammad Haris Khan and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

HAPACT: A Benchmark For Human-Centric Physical Impact Localization in Movies

Youngrae Kim, Yejin Jang, Eunho Kim, Youjin Sung and 3 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

SCG-HF: Semantic Consistency Grouping for Hierarchical Fusion in Video Emotion Recognition

Muci Li, Yujing Rao, He Li, Mang Ye

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

DSAD: Dynamic Soft Anisotropic Diagrams for Reduced-Order Video Representation

Zhiyang Dou, Laki Iinbor, Wojciech Matusik

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

As the Story Unfolds: Watching a Film and Identifying Characters as a Human Does

Zhongrui Gui, Junyu Xie, Tengda Han, Weidi Xie and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Video Stitching from Multiple Moving Cameras

Shira Ifergane, Roy Amoyal, Shahar Benishay, Oren Freifeld

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Behaviour4All: A Dependency-Aware Toolkit for in-the-wild Facial Behaviour Analysis

Dimitrios Kollias, Chunchang Shao, Odysseus Kaloidas, Ioannis Patras

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

From Matching to Reasoning: Query-Aware Long Video Summarization

Mingu Kang, Sumin Kim, Hyunjin Lee, Sungmin Yang and 2 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute

Ali Salamatian, Anthony Fuller, Pritam Sarkar, James Green and 2 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Q-Focus: Let the Question Guide What to See in Long Videos

Junbo Qiao, Xinning Chai, Dong Fang, Sifa Xie and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

The Prestige: Benchmarking Cognitive Visual Reasoning using Magic Tricks

Shuo Wen, Beixi Du, Edwin Meriaux, Junming Shi and 4 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

PIVOT: A Unified Agentic Framework for Streaming Long-Video Understanding

Qiushi Lyu, Qianlan Yang, Ziqi Pang, Yu-Xiong Wang and 1 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

HyrCap: Hybrid Rank-Calibration of Action Proposals for Temporal Event Understanding

Rui Chen, Xingyu Chen, Pengxin Xu, Kai Chen and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

TF-PRVR: Training-Free Partially Relevant Video Retrieval for Real-World Generalization

Giyeol Kim, Chanho Eom

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Where Do We (Not) Need Temporal Context in Low-Resource Video Task Adaptation?

Luc Sträter, Hazel Doughty

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Elephant in the Fridge: Constant-Memory Frame Packing for Long Video Understanding

Shuo Gao, Chenhao Zheng, Jason Ren

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

ViewSAM: Learning View-aware Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking

Jiawei Ge, Xintian Zhang, Jiuxin Cao, Bo Liu and 8 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

Perception, Not Reasoning, Limits Visual Theory of Mind

Mohamed Rayan Barhdadi, Syed Talal Wasim, Jürgen Gall, Erchin Serpedin and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

UTOPI: Efficient Egocentric Long-Video Understanding in AR via User-Guided Token Pre-Compression

ziqi wang, Su Chen, Qiance Tang, Jieyu Lin and 3 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Swift Sampling: Selecting Temporal Surprises via Taylor Series

Swift Sampling uses Taylor-series projections of visual feature trajectories to select temporally surprising frames, cutting overhead by 30x while boosting long-video accuracy up to 12.5 points.

Dahye Kim, Bhuvan Sachdeva, Karan Uppal, Naman Gupta and 2 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 7 on Hugging Face

Higher-Order Cell Tracking Transformer

HOCT is an edge-centric transformer that links cell detections across time via 3D geometric attention, achieving state-of-the-art tracking without pretrained encoders and reducing errors 59% with minimal annotations.

Jordão Bragantini, Ilan Theodoro, Loic A Royer

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

How You Move Tells What You'll Do: Trajectory-Conditioned Egocentric Prediction

TrajPilot predicts future camera trajectories from egocentric video to condition action prediction, outperforming language-conditioned planners on procedural planning and anticipation.

SeJoon Jun, Hai Nguyen-Truong, Luigi Seminara, Lorenzo Torresani

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Why Latent Actions Fail, and How to Prevent It

Standard reconstruction in latent action models encodes exogenous future state, but endogenous representations and action supervision prevent this failure.

Jung Min Lee, Taehyun Cho, Li Zhao, Jungwoo Lee

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception

Behavioral geometric supervision aligns video foundation models with human social perception by matching embedding geometry to human similarity judgments, nearly tripling V-JEPA 2.1 performance past language baselines and developing interpretable social attributes with zero-shot transfer.

Kathy Garcia, Leyla Isik

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Principia: Relational Physics Tests for Video Models

Principia benchmarks video generators via calibration-independent relational physics consistency across eight Newtonian phenomena, finding top models score below 0.42 despite high VBench ratings.

Varun V Thozhiyoor, Shivam Tripathi, Venkatesh Babu Radhakrishnan, Anand Bhattad

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026 · ▲ 18 on Hugging Face

Rethinking the Readout: Unlocking Video Backbones for AI-Generated Video Detection

Standard video backbone readouts suppress patch-level temporal dynamics needed to detect AI-generated videos; a lightweight velocity-gated patch profiling readout reaches 95.28 AUC on frozen backbones.

Manni Cui, Ziheng Qin, ZiAn Wang, Ruiqi Liu and 7 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer

OmniShotCut reframes shot boundary detection as structured relational prediction via a shot-query transformer, outperforming existing methods on a new synthetic benchmark.

Boyang Wang, Guangyi Xu, Jiahui Zhang, Zhipeng Tang and 1 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

HOPE: Hand-Object Pressure Estimation from Monocular Videos

HOPE predicts temporally evolving per-vertex hand pressure and contact from monocular video via a vertex-anchored video transformer, generalizing across objects and bare-hand settings.

Subin Jeon, Byungjun Kim, Hanbyul Joo

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

UGO: Unified Architecture for General Multi-Object Tracking by Segmentation

UGO unifies GMOT via an exemplar-conditioned detection and instance-propagation architecture with consolidation and hierarchical memory, achieving state-of-the-art results.

Jer Pelhan, Alan Lukezic, Matej Kristan

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

3DSPA: A 3D Semantic Point Autoencoder for Evaluating Video Realism

3DSPA is a reference-free 3D semantic point autoencoder that evaluates video realism by integrating point trajectories, depth, and semantic features to detect physical violations and motion artifacts with high human alignment.

Bhavik Chandna, Kelsey Allen

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

GazeFlow: From Human Gaze Behavior to Generative Egocentric Gaze Prediction

GazeFlow models egocentric gaze as a joint distribution via conditional flow matching, achieving state-of-the-art per-frame accuracy and more human-like temporal dynamics by combining bottom-up visual features with top-down task queries.

Sheng Zhao, Weikai Lin, Yuhao Zhu

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Learning to Evolve Scenes: Reasoning about Human Activities with Scene Graphs

SG-Ego extends Ego4D with time-evolving scene graphs and GLEN reasons over them to model activity-driven scene dynamics, outperforming raw video and MLLM baselines on retrieval and long-horizon reasoning.

Francesca Pistilli, Simone Alberto Peirone, Giuseppe Averta

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

Video-Zero: Self-Evolution Video Understanding

Video-Zero improves video understanding via annotation-free questioner-solver co-evolution centered on temporally localized evidence, boosting 13 benchmark results.

ruixu zhang, Deyi Ji, Lanyun Zhu, Xuanyi Liu and 3 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026