Yu Dai

Mr. Yu Dai

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
17 July 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
LXLinfeng Xu
Linfeng Xu
Qingbo WuQingbo Wu
Qingbo Wu
LPLili Pan
Lili Pan
FMFanman Meng
Fanman Meng
HLHongliang Li
Hongliang Li
YDYu Dai
Yu Dai
With the rapid development of wearable cameras, it is now feasible to considerably increase the collection of egocentric video for first-person visual perception. However, the development is hindered by a shortage of multi-modal egocentric activity datasets. Furthermore, the catastrophic forgetting problem of multimodal continual activity learning, as a branch of continual learning, has not been thoroughly explored, which makes accumulating a larger collection of multi-modal activity data more urgent. To address this shortage, we propose a multi-modal egocentric activity dataset for continual activity learning named UESTC-MMEA-CL in this paper. The dataset is collected using our self-developed glasses with a first-person camera and wearable sensors, and it contains synchronized data of video, accelerometers, and gyroscopes for 32 types of daily activities performed by 10 participants who wore our glasses. Statistical analysis of the sensor data is given to show the auxiliary effects of activity recognition. We report the results of egocentric activity recognition of three modalities (RGB, acceleration, and gyroscope) separately and jointly on a base network architecture. We thoroughly evaluated four baseline methods with different multimodal combinations to explore the catastrophic forgetting in continual learning on UESTC-MMEA-CL. We hope that the UESTC-MMEA-CL dataset can act as a facilitator for future studies on continual learning for first-person activity recognition in wearable applications. You can download preliminary data from https://ivipclab.github.io/publication\_uestc-mmea-cl/mmea-cl . The data is currently used to solve the problems of multimodal continual learning of activities.

29 July 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
TZTaijin Zhao
Taijin Zhao
HQHeqian Qiu
Heqian Qiu
YDYu Dai
Yu Dai
LWLanxiao Wang
Lanxiao Wang
HMHefei Mei
Hefei Mei
HLHongliang Li
Hongliang Li

19 March 2025 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
BQBenliu Qiu
Benliu Qiu
HQHeqian Qiu
Heqian Qiu
HWHaitao Wen
Haitao Wen
LWLanxiao Wang
Lanxiao Wang
YDYu Dai
Yu Dai
HLHongliang Li
Hongliang Li
Deep networks notoriously suffer from performance deterioration on previous tasks when learning from sequential tasks, i.e., catastrophic forgetting. Recent methods of gradient projection show that the forgetting is resulted from the gradient interference on old tasks and accordingly propose to update the network in an orthogonal direction to the task space. However, these methods assume the task space is invariant and neglect the gradual change between tasks, resulting in sub-optimal gradient projection and a compromise of the continual learning capacity. To tackle this problem, we propose to embed each task subspace into a non-Euclidean manifold, which can naturally capture the change of tasks since the manifold is intrinsically non-static compared to the Euclidean space. Subsequently, we analytically derive the accumulated projection between any two subspaces on the manifold along the geodesic path by integrating an infinite number of intermediate subspaces. Building upon this derivation, we propose a novel geodesic-aligned gradient projection (GAGP) method that harnesses the accumulated projection to mitigate catastrophic forgetting. The proposed method utilizes the geometric structure information on the task manifold by capturing the gradual change between the new and the old tasks. Empirical studies on image classification demonstrate that the proposed method alleviates catastrophic forgetting and achieves on-par or better performance compared to the state-of-the-art approaches.

1 January 2026 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
TZTaijin Zhao
Taijin Zhao
HQHeqian Qiu
Heqian Qiu
YDYu Dai
Yu Dai
LWLanxiao Wang
Lanxiao Wang
FMFanman Meng
Fanman Meng
HLHongliang Li
Hongliang Li

1 April 2024 in arXiv
Verified
Preprint
Open access
PDF file
JJJian Jiao
Jian Jiao
YDYu Dai
Yu Dai
HMHefei Mei
Hefei Mei
HQHeqian Qiu
Heqian Qiu
CGChuanyang Gong
Chuanyang Gong
HLHongliang Li
Hongliang Li
Recent video class-incremental learning usually excessively pursues the accuracy of the newly seen classes and relies on memory sets to mitigate catastrophic forgetting of the old classes. However, limited storage only allows storing a few representative videos. So we propose SNRO, which slightly shifts the features of new classes to remember old classes. Specifically, SNRO contains Examples Sparse(ES) and Early Break(EB). ES decimates at a lower sample rate to build memory sets and uses interpolation to align those sparse frames in the future. By this, SNRO stores more examples under the same memory consumption and forces the model to focus on low-semantic features which are harder to be forgotten. EB terminates the training at a small epoch, preventing the model from overstretching into the high-semantic space of the current task. Experiments on UCF101, HMDB51, and UESTC-MMEA-CL datasets show that SNRO performs better than other approaches while consuming the same memory consumption.

27 June 2025 in arXiv
Verified
Preprint
Open access
PDF file
TZTaijin Zhao
Taijin Zhao
HQHeqian Qiu
Heqian Qiu
YDYu Dai
Yu Dai
LWLanxiao Wang
Lanxiao Wang
FMFanman Meng
Fanman Meng
HLHongliang Li
Hongliang Li
Few-shot object detection (FSOD) aims to detect objects with limited samples for novel classes, while relying on abundant data for base classes. Existing FSOD approaches, predominantly built on the Faster R-CNN detector, entangle objectness recognition and foreground classification within shared feature spaces. This paradigm inherently establishes class-specific objectness criteria and suffers from unrepresentative novel class samples. To resolve this limitation, we propose a Uniform Orthogonal Feature Space (UOFS) optimization framework. First, UOFS decouples the feature space into two orthogonal components, where magnitude encodes objectness and angle encodes classification. This decoupling enables transferring class-agnostic objectness knowledge from base classes to novel classes. Moreover, implementing the disentanglement requires careful attention to two challenges: (1) Base set images contain unlabeled foreground instances, causing confusion between potential novel class instances and backgrounds. (2) Angular optimization depends exclusively on base class foreground instances, inducing overfitting of angular distributions to base classes. To address these challenges, we propose a Hybrid Background Optimization (HBO) strategy: (1) Constructing a pure background base set by removing unlabeled instances in original images to provide unbiased magnitude-based objectness supervision. (2) Incorporating unlabeled foreground instances in the original base set into angular optimization to enhance distribution uniformity. Additionally, we propose a Spatial-wise Attention Disentanglement and Association (SADA) module to address task conflicts between class-agnostic and class-specific tasks. Experiments demonstrate that our method significantly outperforms existing approaches based on entangled feature spaces.