111 citations · 237 across the 25 of their papers we have counts for
7 papers · 1 filter
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…
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…
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…
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…
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…
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…