4 papers
SciVid: Cross-Domain Evaluation of Video Models in Scientific Applications
Yana Hasson, Pauline Luc, Liliane Momeni +10
In recent years, there has been a proliferation of spatiotemporal foundation models in different scientific disciplines. While promising, these models are often domain-specific and…
Scaling 4D Representations
João Carreira, Dilara Gokay, Michael King +32
Scaling has not yet been convincingly demonstrated for pure self-supervised learning from video. However, prior work has focused evaluations on semantic-related tasks $\unicode{x20…
GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labeling
Hritik Bansal, Po-Nien Kung, P. Jeffrey Brantingham +2
Multimodal event argument role labeling (EARL), a task that assigns a role for each event participant (object) in an image is a complex challenge. It requires reasoning over the en…
BootsTAP: Bootstrapped Training for Tracking-Any-Point
Carl Doersch, Pauline Luc, Yi Yang +8
To endow models with greater understanding of physics and motion, it is useful to enable them to perceive how solid surfaces move and deform in real scenes. This can be formalized…