Search Results for author:
Found 3 papers, 2 papers with code
AI-SAM: Automatic and Interactive Segment Anything Model
Interactive approaches, exemplified by the Segment Anything Model (SAM), have shown promise as pre-trained models.
Learning Emotion Representations from Verbal and Nonverbal Communication
We present EmotionCLIP, the first pre-training paradigm to extract visual emotion representations from verbal and nonverbal communication using only uncurated data.
Ranked #2 on
Emotion Recognition in Context
on BoLD
Learning to Adapt to Online Streams with Distribution Shifts
Test-time adaptation (TTA) is a technique used to reduce distribution gaps between the training and testing sets by leveraging unlabeled test data during inference.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
