Search Results for author:
Found 9 papers, 6 papers with code
DAVE: Diagnostic benchmark for Audio Visual Evaluation
Audio-visual understanding is a rapidly evolving field that seeks to integrate and interpret information from both auditory and visual modalities.
Estimating calibration error under label shift without labels
In the face of dataset shift, model calibration plays a pivotal role in ensuring the reliability of machine learning systems.
Linking Surface Facts to Large-Scale Knowledge Graphs
Open Information Extraction (OIE) methods extract facts from natural language text in the form of ("subject"; "relation"; "object") triples.
Multimodal Distillation for Egocentric Action Recognition
The goal of this work is to retain the performance of such a multimodal approach, while using only the RGB frames as input at inference time.
Students taught by multimodal teachers are superior action recognizers
Our approach is based on multimodal knowledge distillation, featuring a multimodal teacher (in the current experiments trained only using object detections, optical flow and RGB frames) and a unimodal student (using only RGB frames as input).
Revisiting spatio-temporal layouts for compositional action recognition
Recognizing human actions is fundamentally a spatio-temporal reasoning problem, and should be, at least to some extent, invariant to the appearance of the human and the objects involved.
Ranked #36 on
Action Classification
on Charades
Decoding Language Spatial Relations to 2D Spatial Arrangements
We address the problem of multimodal spatial understanding by decoding a set of language-expressed spatial relations to a set of 2D spatial arrangements in a multi-object and multi-relationship setting.
Learning to ground medical text in a 3D human atlas
In this paper, we develop a method for grounding medical text into a physically meaningful and interpretable space corresponding to a human atlas.
Self-supervised context-aware COVID-19 document exploration through atlas grounding
In this paper, we aim to develop a self-supervised grounding of Covid-related medical text based on the actual spatial relationships between the referred anatomical concepts.
