Search Results for author:
Found 6 papers, 4 papers with code
AGORA: Avatars in Geography Optimized for Regression Analysis
Additionally, we fine-tune methods on AGORA and show improved performance on both AGORA and 3DPW, confirming the realism of the dataset.
Learning to Train with Synthetic Humans
Here we explore two variations of synthetic data for this challenging problem; a dataset with purely synthetic humans and a real dataset augmented with synthetic humans.
Learning Multi-Human Optical Flow
Therefore, we develop a dataset of multi-human optical flow and train optical flow networks on this dataset.
Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives
This paper introduces Ranking Info Noise Contrastive Estimation (RINCE), a new member in the family of InfoNCE losses that preserves a ranked ordering of positive samples.
Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems
In this work, we study rapid, step-wise improvements of the loss in transformers when being confronted with multi-step decision tasks.
Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Representation Learning
This revealed that the driving factor behind both, the modality gap and the object bias, is the information imbalance between images and captions.
