FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model
Recently, conditional diffusion models have gained popularity in numerous applications due to their exceptional generation ability. However, many existing methods are …
Jiwen yu
Bernard ghanem
•
•
1 min read
EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries
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 …
Jinjie mai
A Unified Continual Learning Framework with General Parameter-Efficient Tuning
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 achieved …
Qiankun gao
Large-capacity and Flexible Video Steganography via Invertible Neural Network
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. …
Chong mou
ETAD: Training Action Detection End to End on a Laptop
Untrimmed video understanding such as temporal action detection (TAD) often suffers from the pain of huge demand for computing resources. Because of long video durations and …
Shuming liu
Owl (observe, watch, listen): Localizing actions in egocentric video via audiovisual temporal context
Temporal action localization (TAL) is an important task extensively explored and improved for third-person videos in recent years. Recent efforts have been made to perform …
Merey ramazanova
Just a Glimpse: Rethinking Temporal Information for Video Continual Learning
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 …
Lama alssum
R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning
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 …
Qiankun gao
End-to-End Active Speaker Detection
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 …
Juan leon alcazar
When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search
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 …
Guocheng qian