Search Results for author:
Found 6 papers, 0 papers with code
Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters
Our MLM filter can generalize to different models and tasks, and be used as a drop-in replacement for CLIPScore.
The Devil is in the Details: A Deep Dive into the Rabbit Hole of Data Filtering
DataComp is a new benchmark dedicated to evaluating different methods for data filtering.
Graph Inverse Reinforcement Learning from Diverse Videos
Research on Inverse Reinforcement Learning (IRL) from third-person videos has shown encouraging results on removing the need for manual reward design for robotic tasks.
Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering
The temporal optimal transport module enables our approach to learn effective representations for unsupervised activity segmentation.
Learning by Aligning Videos in Time
To overcome this problem, we propose a temporal regularization term (i. e., Contrastive-IDM) which encourages different frames to be mapped to different points in the embedding space.
Towards Anomaly Detection in Dashcam Videos
We apply: (i) one-class classification loss and (ii) reconstruction-based loss, for anomaly detection on RetroTrucks as well as on existing static-camera datasets.
