Search Results for author:
Found 7 papers, 6 papers with code
Every Shot Counts: Using Exemplars for Repetition Counting in Videos
We propose an exemplar-based approach that discovers visual correspondence of video exemplars across repetitions within target videos.
Ranked #1 on
Repetitive Action Counting
on UCFRep
MILA: Memory-Based Instance-Level Adaptation for Cross-Domain Object Detection
A source sample is considered suitable if it differs from the target sample only in domain, without differences in unimportant characteristics such as orientation and color, which can hinder the model's focus on aligning the domain difference.
Use Your Head: Improving Long-Tail Video Recognition
We demonstrate that, unlike naturally-collected video datasets and existing long-tail image benchmarks, current video benchmarks fall short on multiple long-tailed properties.
Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition
Long-tailed datasets, where head classes comprise much more training samples than tail classes, cause recognition models to get biased towards the head classes.
Ranked #12 on
Long-tail Learning
on Places-LT
Class-Difficulty Based Methods for Long-Tailed Visual Recognition
Further, we use the difficulty measures of each class to design a novel weighted loss technique called `class-wise difficulty based weighted (CDB-W) loss' and a novel data sampling technique called `class-wise difficulty based sampling (CDB-S)'.
Scale-free networks may not necessarily witness cooperation
Networks with a scale-free degree distribution are widely thought to promote cooperation in various games.
Physics and Society Statistical Mechanics Social and Information Networks Populations and Evolution
Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance
We claim that the 'difficulty' of a class as perceived by the model is more important to determine the weighting.
Ranked #1 on
Long-tail Learning
on EGTEA
