User profiles for Yujie Zhong
Yujie ZhongMeituan Inc. Verified email at robots.ox.ac.uk Cited by 1174 |
Exploring classification equilibrium in long-tailed object detection
The conventional detectors tend to make imbalanced classification and suffer performance
drop, when the distribution of the training data is severely skewed. In this paper, we propose …
drop, when the distribution of the training data is severely skewed. In this paper, we propose …
Tood: Task-aligned one-stage object detection
One-stage object detection is commonly implemented by optimizing two sub-tasks: object
classification and localization, using heads with two parallel branches, which might lead to a …
classification and localization, using heads with two parallel branches, which might lead to a …
Mechanisms of change in gel water-holding capacity of myofibrillar proteins affected by lipid oxidation: The role of protein unfolding and cross-linking
Y Jiang, D Li, J Tu, Y Zhong, D Zhang, Z Wang, X Tao - Food Chemistry, 2021 - Elsevier
This work explored the effects of protein unfolding and cross-linking induced by lipid oxidation
(linoleic acid, OLA) on the gel water-holding capacity (WHC) of beef myofibrillar proteins (…
(linoleic acid, OLA) on the gel water-holding capacity (WHC) of beef myofibrillar proteins (…
Cross-architecture self-supervised video representation learning
In this paper, we present a new cross-architecture contrastive learning (CACL) framework
for self-supervised video representation learning. CACL consists of a 3D CNN and a video …
for self-supervised video representation learning. CACL consists of a 3D CNN and a video …
Tridet: Temporal action detection with relative boundary modeling
In this paper, we present a one-stage framework TriDet for temporal action detection. Existing
methods often suffer from imprecise boundary predictions due to the ambiguous action …
methods often suffer from imprecise boundary predictions due to the ambiguous action …
Promptdet: Towards open-vocabulary detection using uncurated images
The goal of this work is to establish a scalable pipeline for expanding an object detector
towards novel/unseen categories, using zero manual annotations. To achieve that, we make the …
towards novel/unseen categories, using zero manual annotations. To achieve that, we make the …
Dearkd: Data-efficient early knowledge distillation for vision transformers
Transformers have been successfully applied to computer vision due to its powerful modelling
capacity with self-attention. However, the good performance of transformers heavily …
capacity with self-attention. However, the good performance of transformers heavily …
React: Temporal action detection with relational queries
This work aims at advancing temporal action detection (TAD) using an encoder-decoder
framework with action queries, similar to DETR, which has shown great success in object …
framework with action queries, similar to DETR, which has shown great success in object …
A review of automatic recognition technology for bird vocalizations in the deep learning era
Birds are considered critical indicators of ecosystem condition. Automatic recording devices
have emerged as a trending tool to assist field observations, contributing to biodiversity …
have emerged as a trending tool to assist field observations, contributing to biodiversity …
Ghostvlad for set-based face recognition
The objective of this paper is to learn a compact representation of image sets for template-based
face recognition. We make the following contributions: first, we propose a network …
face recognition. We make the following contributions: first, we propose a network …