Search Results for author: Megha Nawhal

Found 9 papers, 2 papers with code

Rethinking Learning Approaches for Long-Term Action Anticipation

1 code implementation20 Oct 2022 Megha Nawhal, Akash Abdu Jyothi, Greg Mori

Action anticipation involves predicting future actions having observed the initial portion of a video.

Action Anticipation Future prediction +1

Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation

no code implementations ECCV 2020 Mengyao Zhai, Lei Chen, JiaWei He, Megha Nawhal, Frederick Tung, Greg Mori

In contrast, we propose a parameter efficient framework, Piggyback GAN, which learns the current task by building a set of convolutional and deconvolutional filters that are factorized into filters of the models trained on previous tasks.

Activity Graph Transformer for Temporal Action Localization

no code implementations21 Jan 2021 Megha Nawhal, Greg Mori

Detecting and localizing action instances in untrimmed videos requires reasoning over multiple action instances in a video.

Ranked #3 on Temporal Action Localization on THUMOS’14 (mAP IOU@0.1 metric)

Temporal Action Localization

Variational Selective Autoencoder

no code implementations pproximateinference AABI Symposium 2019 Yu Gong, Hossein Hajimirsadeghi, JiaWei He, Megha Nawhal, Thibaut Durand, Greg Mori

Despite promising progress on unimodal data imputation (e. g. image inpainting), models for multimodal data imputation are far from satisfactory.

Image Inpainting Imputation

Continuous Graph Flow

no code implementations7 Aug 2019 Zhiwei Deng, Megha Nawhal, Lili Meng, Greg Mori

In this paper, we propose Continuous Graph Flow, a generative continuous flow based method that aims to model complex distributions of graph-structured data.

Density Estimation Graph Generation

Cannot find the paper you are looking for? You can Submit a new open access paper.