research
∙
08/31/2023
Socratis: Are large multimodal models emotionally aware?
Existing emotion prediction benchmarks contain coarse emotion labels whi...
share
research
∙
07/24/2023
Multiscale Video Pretraining for Long-Term Activity Forecasting
Long-term activity forecasting is an especially challenging research pro...
research
∙
07/11/2023
EgoAdapt: A multi-stream evaluation study of adaptation to real-world egocentric user video
In egocentric action recognition a single population model is typically ...
research
∙
03/28/2023
Language-Guided Audio-Visual Source Separation via Trimodal Consistency
We propose a self-supervised approach for learning to perform audio sour...
research
∙
07/26/2022
NewsStories: Illustrating articles with visual summaries
Recent self-supervised approaches have used large-scale image-text datas...
research
∙
10/20/2021
Look at What I'm Doing: Self-Supervised Spatial Grounding of Narrations in Instructional Videos
We introduce the task of spatially localizing narrated interactions in v...
research
∙
09/16/2020
Detecting Cross-Modal Inconsistency to Defend Against Neural Fake News
Large-scale dissemination of disinformation online intended to mislead o...
research
∙
09/27/2019
wMAN: Weakly-supervised Moment Alignment Network for Text-based Video Segment Retrieval
Given a video and a sentence, the goal of weakly-supervised video moment...
research
∙
08/22/2019
Learning Similarity Conditions Without Explicit Supervision
Many real-world tasks require models to compare images along multiple si...
research
∙
08/17/2019