Search Results for author:
Found 4 papers, 2 papers with code
Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation
Predictive multiplicity refers to the phenomenon in which classification tasks may admit multiple competing models that achieve almost-equally-optimal performance, yet generate conflicting outputs for individual samples.
VALHALLA: Visual Hallucination for Machine Translation
In particular, given a source sentence an autoregressive hallucination transformer is used to predict a discrete visual representation from the input text, and the combined text and hallucinated representations are utilized to obtain the target translation.
Temporal Relevance Analysis for Video Action Models
In this paper, we provide a deep analysis of temporal modeling for action recognition, an important but underexplored problem in the literature.
Can An Image Classifier Suffice For Action Recognition?
We explore a new perspective on video understanding by casting the video recognition problem as an image recognition task.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
