activity
20172022
most citedCompressing Recurrent Neural Network with Tensor Train

111 citations · 237 across the 25 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV20221 cited

Instance-level Heterogeneous Domain Adaptation for Limited-labeled Sketch-to-Photo Retrieval

Fan Yang, Yang Wu, Zheng Wang +3

Although sketch-to-photo retrieval has a wide range of applications, it is costly to obtain paired and rich-labeled ground truth. Differently, photo retrieval data is easier to acq…

cs.CV2022

Actor-identified Spatiotemporal Action Detection -- Detecting Who Is Doing What in Videos

Fan Yang, Norimichi Ukita, Sakriani Sakti +1

The success of deep learning on video Action Recognition (AR) has motivated researchers to progressively promote related tasks from the coarse level to the fine-grained level. Comp…

cs.CV2020

Image Captioning with Visual Object Representations Grounded in the Textual Modality

Dušan Variš, Katsuhito Sudoh, Satoshi Nakamura

We present our work in progress exploring the possibilities of a shared embedding space between textual and visual modality. Leveraging the textual nature of object detection label…

cs.CV2020

ReMOTS: Self-Supervised Refining Multi-Object Tracking and Segmentation

Fan Yang, Xin Chang, Chenyu Dang +4

We aim to improve the performance of Multiple Object Tracking and Segmentation (MOTS) by refinement. However, it remains challenging for refining MOTS results, which could be attri…

cs.CV2019

Using Panoramic Videos for Multi-person Localization and Tracking in a 3D Panoramic Coordinate

Fan Yang, Feiran Li, Yang Wu +2

3D panoramic multi-person localization and tracking are prominent in many applications, however, conventional methods using LiDAR equipment could be economically expensive and also…

cs.CV2019

Make Skeleton-based Action Recognition Model Smaller, Faster and Better

Fan Yang, Sakriani Sakti, Yang Wu +1

Although skeleton-based action recognition has achieved great success in recent years, most of the existing methods may suffer from a large model size and slow execution speed. To…