8 citations · 37 across the 24 of their papers we have counts for
24 papers
SEVERE++: Evaluating Benchmark Sensitivity in Generalization of Video Representation Learning
Fida Mohammad Thoker, Letian Jiang, Chen Zhao +4
Continued advances in self-supervised learning have led to significant progress in video representation learning, offering a scalable alternative to supervised approaches by removi…
SMILE: Infusing Spatial and Motion Semantics in Masked Video Learning
Fida Mohammad Thoker, Letian Jiang, Chen Zhao +1
Masked video modeling, such as VideoMAE, is an effective paradigm for video self-supervised learning (SSL). However, they are primarily based on reconstructing pixel-level details…
BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
Shuming Liu, Chen Zhao, Tianqi Xu +1
Large video-language models (VLMs) have demonstrated promising progress in various video understanding tasks. However, their effectiveness in long-form video analysis is constraine…
CO2Wounds-V2: Extended Chronic Wounds Dataset From Leprosy Patients
Karen Sanchez, Carlos Hinojosa, Olinto Mieles +3
Chronic wounds pose an ongoing health concern globally, largely due to the prevalence of conditions such as diabetes and leprosy's disease. The standard method of monitoring these…
Harnessing Temporal Causality for Advanced Temporal Action Detection
Shuming Liu, Lin Sui, Chen-Lin Zhang +3
As a fundamental task in long-form video understanding, temporal action detection (TAD) aims to capture inherent temporal relations in untrimmed videos and identify candidate actio…
Hybrid Structure-from-Motion and Camera Relocalization for Enhanced Egocentric Localization
Jinjie Mai, Abdullah Hamdi, Silvio Giancola +2
We built our pipeline EgoLoc-v1, mainly inspired by EgoLoc. We propose a model ensemble strategy to improve the camera pose estimation part of the VQ3D task, which has been proven…
End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames
Shuming Liu, Chen-Lin Zhang, Chen Zhao +1
Recently, temporal action detection (TAD) has seen significant performance improvement with end-to-end training. However, due to the memory bottleneck, only models with limited sca…
HD-Fusion: Detailed Text-to-3D Generation Leveraging Multiple Noise Estimation
Jinbo Wu, Xiaobo Gao, Xing Liu +5
In this paper, we study Text-to-3D content generation leveraging 2D diffusion priors to enhance the quality and detail of the generated 3D models. Recent progress (Magic3D) in text…
Just a Glimpse: Rethinking Temporal Information for Video Continual Learning
Lama Alssum, Juan Leon Alcazar, Merey Ramazanova +2
Class-incremental learning is one of the most important settings for the study of Continual Learning, as it closely resembles real-world application scenarios. With constrained mem…
Large-capacity and Flexible Video Steganography via Invertible Neural Network
Chong Mou, Youmin Xu, Jiechong Song +3
Video steganography is the art of unobtrusively concealing secret data in a cover video and then recovering the secret data through a decoding protocol at the receiver end. Althoug…
FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model
Jiwen Yu, Yinhuai Wang, Chen Zhao +2
Recently, conditional diffusion models have gained popularity in numerous applications due to their exceptional generation ability. However, many existing methods are training-requ…
A Unified Continual Learning Framework with General Parameter-Efficient Tuning
Qiankun Gao, Chen Zhao, Yifan Sun +4
The "pre-training downstream adaptation" presents both new opportunities and challenges for Continual Learning (CL). Although the recent state-of-the-art in CL is ach…
EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries
Jinjie Mai, Abdullah Hamdi, Silvio Giancola +2
With the recent advances in video and 3D understanding, novel 4D spatio-temporal methods fusing both concepts have emerged. Towards this direction, the Ego4D Episodic Memory Benchm…
Estimating more camera poses for ego-centric videos is essential for VQ3D
Jinjie Mai, Chen Zhao, Abdullah Hamdi +2
Visual queries 3D localization (VQ3D) is a task in the Ego4D Episodic Memory Benchmark. Given an egocentric video, the goal is to answer queries of the form "Where did I last see o…
Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization
Chen Zhao, Shuming Liu, Karttikeya Mangalam +1
Temporal action localization (TAL) requires long-form reasoning to predict actions of various durations and complex content. Given limited GPU memory, training TAL end to end (i.e.…
ETAD: Training Action Detection End to End on a Laptop
Shuming Liu, Mengmeng Xu, Chen Zhao +2
Temporal action detection (TAD) with end-to-end training often suffers from the pain of huge demand for computing resources due to long video duration. In this work, we propose an…
When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search
Guocheng Qian, Xuanyang Zhang, Guohao Li +5
The key challenge in neural architecture search (NAS) is designing how to explore wisely in the huge search space. We propose a new NAS method called TNAS (NAS with trees), which i…
SegTAD: Precise Temporal Action Detection via Semantic Segmentation
Chen Zhao, Merey Ramazanova, Mengmeng Xu +1
Temporal action detection (TAD) is an important yet challenging task in video analysis. Most existing works draw inspiration from image object detection and tend to reformulate it…
End-to-End Active Speaker Detection
Juan Leon Alcazar, Moritz Cordes, Chen Zhao +1
Recent advances in the Active Speaker Detection (ASD) problem build upon a two-stage process: feature extraction and spatio-temporal context aggregation. In this paper, we propose…
R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning
Qiankun Gao, Chen Zhao, Bernard Ghanem +1
Class-Incremental Learning (CIL) struggles with catastrophic forgetting when learning new knowledge, and Data-Free CIL (DFCIL) is even more challenging without access to the traini…
OWL (Observe, Watch, Listen): Audiovisual Temporal Context for Localizing Actions in Egocentric Videos
Merey Ramazanova, Victor Escorcia, Fabian Caba Heilbron +2
Egocentric videos capture sequences of human activities from a first-person perspective and can provide rich multimodal signals. However, most current localization methods use thir…
MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions
Mattia Soldan, Alejandro Pardo, Juan León Alcázar +4
The recent and increasing interest in video-language research has driven the development of large-scale datasets that enable data-intensive machine learning techniques. In comparis…
Ego4D: Around the World in 3,000 Hours of Egocentric Video
Kristen Grauman, Andrew Westbury, Eugene Byrne +82
We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outd…
Video Self-Stitching Graph Network for Temporal Action Localization
Chen Zhao, Ali Thabet, Bernard Ghanem
Temporal action localization (TAL) in videos is a challenging task, especially due to the large variation in action temporal scales. Short actions usually occupy a major proportion…