Search Results for author:
Found 11 papers, 7 papers with code
Shuffle and Attend: Video Domain Adaptation
As the first novelty, we propose an attention mechanism which focuses on more discriminative clips and directly optimizes for video-level (cf.
Ranked #3 on
Unsupervised Domain Adaptation
on UCF-HMDB
Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval
There has been significant attention to the research on dense video captioning, which aims to automatically localize and caption all events within untrimmed video.
Ranked #3 on
Dense Video Captioning
on YouCook2
MobileSAMv2: Faster Segment Anything to Everything
The efficiency bottleneck of SegEvery with SAM, however, lies in its mask decoder because it needs to first generate numerous masks with redundant grid-search prompts and then perform filtering to obtain the final valid masks.
DEVIAS: Learning Disentangled Video Representations of Action and Scene for Holistic Video Understanding
Disentangled action and scene representations could be beneficial for both in-context and out-of-context video understanding.
CAST: Cross-Attention in Space and Time for Video Action Recognition
In this work, we propose a novel two-stream architecture, called Cross-Attention in Space and Time (CAST), that achieves a balanced spatio-temporal understanding of videos using only RGB input.
Ranked #7 on
Action Recognition
on EPIC-KITCHENS-100
Contrastive encoder pre-training-based clustered federated learning for heterogeneous data
Together, self-supervised pre-training and client clustering can be crucial components for tackling the data heterogeneity issues of FL.
GLAD: Global-Local View Alignment and Background Debiasing for Unsupervised Video Domain Adaptation with Large Domain Gap
We specifically focus on scenarios with a substantial domain gap, in contrast to existing works primarily deal with small domain gaps between labeled source domains and unlabeled target domains.
One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Era
Overall, this work is the first to survey ChatGPT with a comprehensive review of its underlying technology, applications, and challenges.
StyleMix: Separating Content and Style for Enhanced Data Augmentation
In spite of the great success of deep neural networks for many challenging classification tasks, the learned networks are vulnerable to overfitting and adversarial attacks.
Learning Representational Invariances for Data-Efficient Action Recognition
Data augmentation is a ubiquitous technique for improving image classification when labeled data is scarce.
Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition
We validate the effectiveness of our method by transferring our pre-trained model to three different tasks, including action classification, temporal localization, and spatio-temporal action detection.
