Qiong Liu

Qiong Liu

Auto-generated profile, based on publicly available information

Qiong Liu

CloudWalk Technology, Shanghai, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 October 2023
Verified
Conference Paper
Open access
CZChunhui Zhang
Chunhui Zhang
XSXin Sun
Xin Sun
YYYiqian Yang
Yiqian Yang
LLLi Liu
Li Liu
QLQiong Liu
Qiong Liu
YWYanfeng Wang
Yanfeng Wang

26 February 2023
Verified
Book Chapter
Closed access
PDF file
CZChunhui Zhang
Chunhui Zhang
YCYixiong Chen
Yixiong Chen
LLLi Liu
Li Liu
QLQiong Liu
Qiong Liu
XZXi Zhou
Xi Zhou

16 April 2024 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
XSXin Sun
Xin Sun
XWXuan Wang
Xuan Wang
QLQiong Liu
Qiong Liu
XZXi Zhou
Xi Zhou
The weakly-supervised audio-visual video parsing (AVVP) task aims toparse a video into temporal events and predict their modality-specific categories. Current works primarily focus on refining training strategies and follow the framework fusing signals only at the segment level. However, they miss the point that video events, being composed of consecutive segments, require the integration of both local and global contexts to fully capture their essence. In this letter, we present the L ocal- G lobal F usion Net work ( LGFNet ), designed to facilitate multi-level interaction between audio and visual signals. Specifically, we create a two-dimensional map to generate multi-scale event proposals for both audio and visual modalities. Subsequently, we fuse audio and visual signals at both segment and event levels with a novel boundary-aware feature aggregation method, enabling the simultaneous capture of local and global information. To enhance the temporal alignment between the two modalities, we employ segment-level and event-level contrastive learning. In-depth experiments demonstrate the superiority of our LGFNet.

16 April 2024 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
ZSZhiqiang Shen
Zhiqiang Shen
LWLongguang Wang
Longguang Wang
YGYulan Guo
Yulan Guo
QLQiong Liu
Qiong Liu
XZXi Zhou
Xi Zhou
The robustness to spatio-temporal sampling is significant for point cloud video understanding. Previous works overlook this issue and usually suffer notable performance drops when point densities and frame rates are changed. To remedy this, we propose a point spatio-temporal pyramid (PoST-Py) to improve the sampling robustness of point cloud video modeling. Specifically, we propose a pluggable PoST-Py to collect multi-scale feature maps from different layers of the backbone. Then, these features are integrated into a unified representation. This allows the model to capture multi-scale spatio-temporal information simultaneously. In addition, we employ the temporal cardinality difference to enhance the features to capture motion information. Extensive experiments show that PoST-Py achieves state-of-the-art performance, particularly with a notable improvement of over 2% under varying point sampling. This demonstrates the improved robustness of our method.