Search Results for author:
Found 8 papers, 5 papers with code
CASP: Compression of Large Multimodal Models Based on Attention Sparsity
In this work, we propose an extreme compression technique for Large Multimodal Models (LMMs).
ESCAPE: Energy-based Selective Adaptive Correction for Out-of-distribution 3D Human Pose Estimation
For OOD samples, we propose a novel self-consistency adaptation loss to update the correction network by leveraging the constraining relationship between distal keypoints and proximal keypoints (shoulders, hips), via a second ``reverse" network.
GOLD: Generalized Knowledge Distillation via Out-of-Distribution-Guided Language Data Generation
Knowledge distillation from LLMs is essential for the efficient deployment of language models.
Ranked #1 on
Data-free Knowledge Distillation
on QNLI
PoseGen: Learning to Generate 3D Human Pose Dataset with NeRF
The objective of PoseGen is to learn a distribution of data that maximizes the prediction error of a given pre-trained model.
ETran: Energy-Based Transferability Estimation
This is the first work that proposes transferability estimation for object detection task.
Ranked #1 on
Transferability
on classification benchmark
Automatic Labeling of Parkinson’s Disease Gait Videos with Weak Supervision
The method obtained state-of-the-art results on the Human3. 6M dataset.
AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation
To this end, we propose AdaptPose, an end-to-end framework that generates synthetic 3D human motions from a source dataset and uses them to fine-tune a 3D pose estimator.
TriPose: A Weakly-Supervised 3D Human Pose Estimation via Triangulation from Video
Estimating 3D human poses from video is a challenging problem.
Ranked #13 on
Weakly-supervised 3D Human Pose Estimation
on Human3.6M
