Yue Feng

Yue Feng

Auto-generated profile, based on publicly available information

Yue Feng

Nanjing University of Aeronautics and Astronautics, Nanjing, 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
YFYue Feng
Yue Feng
ZZZhengye Zhang
Zhengye Zhang
QRQuan Rong
Quan Rong
LWLimin Wang
Limin Wang
JQJie Qin
Jie Qin
Temporal action detection (TAD) aims to localize the start and end frames of actions in untrimmed videos, which is a challenging task due to the similarity of adjacent frames and the ambiguity of action boundaries. Previous methods often generate coarse proposals first and then perform proposal-based refinement, which is coupled with prior action detectors and leads to proposal-oriented offsets. However, this paradigm increases the training difficulty of the TAD model and is heavily influenced by the quantity and quality of the proposals. To address the above issues, we decouple the refinement process from conventional TAD methods and propose a learnable, proposal-free refinement method for fine boundary localization, named RefineTAD. We first propose a multi-level refinement module to generate multi-scale boundary offsets, score offsets and boundary-aware probability at each time point based on the feature pyramid. Then, we propose an offset focusing strategy to progressively refine the predicted results of TAD models in a coarse-to-fine manner with our multi-scale offsets. We perform extensive experiments on three challenging datasets and demonstrate that our RefineTAD significantly improves the state-of-the-art TAD methods with minimal computational overhead.

26 May 2026 in Machine Intelligence Research
Verified
Journal Article
Closed access
YFYue Feng
Yue Feng
ZYZiyi Yan
Ziyi Yan
YJYizhen Jia
Yizhen Jia
ECEthan Q. Chen
Ethan Q. Chen
JQJie Qin
Jie Qin