Search Results for author:
Found 11 papers, 3 papers with code
Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment
Learning to localize temporal boundaries of procedure steps in instructional videos is challenging due to the limited availability of annotated large-scale training videos.
MCTR: Multi Camera Tracking Transformer
MCTR leverages end-to-end detectors like DEtector TRansformer (DETR) to produce detections and detection embeddings independently for each camera view.
Learning from Synthetic Human Group Activities
The study of complex human interactions and group activities has become a focal point in human-centric computer vision.
Differentiable JPEG: The Devil is in the Details
the input image, the JPEG quality, the quantization tables, and the color conversion parameters.
Deep Video Codec Control for Vision Models
To overcome the deterioration of vision performance, this paper presents the first end-to-end learnable deep video codec control that considers both bandwidth constraints and downstream deep vision performance, while adhering to existing standardization.
M3Act: Learning from Synthetic Human Group Activities
The study of complex human interactions and group activities has become a focal point in human-centric computer vision.
Learning Higher-order Object Interactions for Keypoint-based Video Understanding
Specifically, KeyNet introduces the use of object based keypoint information to capture context in the scene.
Source-Free Video Domain Adaptation With Spatial-Temporal-Historical Consistency Learning
Source-free domain adaptation (SFDA) is an emerging research topic that studies how to adapt a pretrained source model using unlabeled target data.
Source-Free Domain Adaptation
Unsupervised Domain Adaptation
Memorization in Deep Neural Networks: Does the Loss Function matter?
Deep Neural Networks, often owing to the overparameterization, are shown to be capable of exactly memorizing even randomly labelled data.
Scalable Data Balancing for Unlabeled Satellite Imagery
Collecting fully annotated datasets is challenging, especially for large scale satellite systems such as the unlabeled NASA's 35 PB Earth Imagery dataset.
Adaptive Sample Selection for Robust Learning under Label Noise
Deep Neural Networks (DNNs) have been shown to be susceptible to memorization or overfitting in the presence of noisily-labelled data.
Ranked #38 on
Image Classification
on Clothing1M
Image Classification
Image Classification with Label Noise
+1
