Author name cluster

Tingting Chen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

1 author row

NeurIPS Conference 2025 Conference Paper

GeoComplete: Geometry-Aware Diffusion for Reference-Driven Image Completion

Beibei Lin
Tingting Chen
Robby Tan

Reference-driven image completion, which restores missing regions in a target view using additional images, is particularly challenging when the target view differs significantly from the references. Existing generative methods rely solely on diffusion priors and, without geometric cues such as camera pose or depth, often produce misaligned or implausible content. We propose GeoComplete, a novel framework that incorporates explicit 3D structural guidance to enforce geometric consistency in the completed regions, setting it apart from prior image-only approaches. GeoComplete introduces two key ideas: conditioning the diffusion process on projected point clouds to infuse geometric information, and applying target-aware masking to guide the model toward relevant reference cues. The framework features a dual-branch diffusion architecture. One branch synthesizes the missing regions from the masked target, while the other extracts geometric features from the projected point cloud. Joint self-attention across branches ensures coherent and accurate completion. To address regions visible in references but absent in the target, we project the target view into each reference to detect occluded areas, which are then masked during training. This target-aware masking directs the model to focus on useful cues, enhancing performance in difficult scenarios. By integrating a geometry-aware dual-branch diffusion architecture with a target-aware masking strategy, GeoComplete offers a unified and robust solution for geometry-conditioned image completion. Experiments show that GeoComplete achieves a 17. 1% PSNR improvement over state-of-the-art methods, significantly boosting geometric accuracy while maintaining high visual quality.

PDF Details

EAAI Journal 2025 Journal Article

Leveraging deep reinforcement learning to optimize linear quadratic regulator parameters for leader-follower formation control

Zhi Wang
Yun Ling
Min Ma
Tingting Chen

The widespread application of robotic formations in various fields, from exploration missions to precision agricultural operations, has highlighted the urgent need for studying and optimizing formation control techniques. This paper aims to enhance the full-process control of a leader-follower formation system, encompassing both formation establishment and maintenance. Firstly, an algorithm is designed to autonomously assign team roles to follower robots in a distributed fashion, thereby generating a virtual goal pose for each follower. Secondly, a combination of a Linear Quadratic Regulator (LQR) controller, based on the Ackermann model, and a Proportional-Derivative (PD) controller is developed for lateral and longitudinal distance control of each robot. Subsequently, an improved Asynchronous Advantage Actor-Critic (A3C) algorithm is utilized to expedite the training process and enable real-time online parameter optimization of the LQR controller. Finally, the Robot Operating System 2 (ROS2)-based formation system and experimental setup are presented, along with a detailed description of the A3C training process. According to both simulation and real-vehicle experiments, the formation control method proposed in this paper demonstrates stable operation and high accuracy in formation maintenance, surpassing other similar methods and the traditional LQR approach.

Details DOI

NeurIPS Conference 2025 Conference Paper

RGB-to-Polarization Estimation: A New Task and Benchmark Study

Beibei Lin
Zifeng Yuan
Tingting Chen

Polarization images provide rich physical information that is fundamentally absent from standard RGB images, benefiting a wide range of computer vision applications such as reflection separation and material classification. However, the acquisition of polarization images typically requires additional optical components, which increases both the cost and the complexity of the applications. To bridge this gap, we introduce a new task: RGB-to-polarization image estimation, which aims to infer polarization information directly from RGB images. In this work, we establish the first comprehensive benchmark for this task by leveraging existing polarization datasets and evaluating a diverse set of state-of-the-art deep learning models, including both restoration-oriented and generative architectures. Through extensive quantitative and qualitative analysis, our benchmark not only establishes the current performance ceiling of RGB-to-polarization estimation, but also systematically reveals the respective strengths and limitations of different model families — such as direct reconstruction versus generative synthesis, and task-specific training versus large-scale pre-training. In addition, we provide some potential directions for future research on polarization estimation. This benchmark is intended to serve as a foundational resource to facilitate the design and evaluation of future methods for polarization estimation from standard RGB inputs.

PDF Details

YNIMG Journal 2024 Journal Article

Atypical prefrontal neural activity during an emotional interference control task in adolescents with autism spectrum disorder: A functional near-infrared spectroscopy study

Tingting Chen
Jiarui Jiang
Mingchao Xu
Yuanfu Dai
Xiaoyan Gao
Changhao Jiang

Hb level in the incongruent condition than the congruent condition, evoking cortical activations primarily in right PFC regions in response to the emotional Flanker effect. In contrast, ASD adolescents failed to exhibit the processing advantage for congruent versus incongruent emotional face in terms of RT, but showed cortical activations primarily in left PFC regions in response to the emotional Flanker effect. These findings suggest that adolescents with ASD rely on different neural strategies to mobilize PFC neural resources to address the difficulties they experience when inhibiting the emotional face.

Details DOI

AAAI Conference 2024 Short Paper

Rider Posture-Based Continuous Authentication with Few-Shot Learning for Mobility Scooters (Student Abstract)

Devan Shah
Ruoqi Huang
Tingting Chen
Murtuza Jadliwala

Current practice of mobility scooter user authentication using physical keys and traditional password-based one-time security mechanisms cannot meet the needs of many mobility scooter riders, especially senior citizens having issues in recalling memory. Now seamless authentication approaches are needed to provide ongoing protection for mobility scooters against takeovers and unauthorized access. Existing continuous authentication techniques do not work well in a mobility scooter setting due to issues such as user comfort, deployment cost and enrollment time, among others. In that direction, our contributions in this research effort are two-fold: (i) we propose a novel system that incorporates advances in few-shot learning, hierarchical processing, and contextual embedding to establish continuous authentication for mobility scooter riders using only posture data. This security system, trained on data collected from real mobility scooter riders, demonstrates quick enrollment and easy deployability, while successfully serving as an unobtrusive first layer of security. (ii) we provide to the research community the largest publicly available repository of mobility scooter riders' body key-points data to enable further research in this direction.

PDF Details DOI

JBHI Journal 2022 Journal Article

Discriminative Cervical Lesion Detection in Colposcopic Images With Global Class Activation and Local Bin Excitation

Tingting Chen
Xuechen Liu
Ruiwei Feng
Wenzhe Wang
Chunnv Yuan
Weiguo Lu
Haizhen He
Honghao Gao

Accurate cervical lesion detection (CLD) methods using colposcopic images are highly demanded in computer-aided diagnosis (CAD) for automatic diagnosis of High-grade Squamous Intraepithelial Lesions (HSIL). However, compared to natural scene images, the specific characteristics of colposcopic images, such as low contrast, visual similarity, and ambiguous lesion boundaries, pose difficulties to accurately locating HSIL regions and also significantly impede the performance improvement of existing CLD approaches. To tackle these difficulties and better capture cervical lesions, we develop novel feature enhancing mechanisms from both global and local perspectives, and propose a new discriminative CLD framework, called CervixNet, with a Global Class Activation (GCA) module and a Local Bin Excitation (LBE) module. Specifically, the GCA module learns discriminative features by introducing an auxiliary classifier, and guides our model to focus on HSIL regions while ignoring noisy regions. It globally facilitates the feature extraction process and helps boost feature discriminability. Further, our LBE module excites lesion features in a local manner, and allows the lesion regions to be more fine-grained enhanced by explicitly modelling the inter-dependencies among bins of proposal feature. Extensive experiments on a number of 9888 clinical colposcopic images verify the superiority of our method (AP $_{. 75}$ = 20. 45) over state-of-the-art models on four widely used metrics.

Details DOI

AAAI Conference 2019 Short Paper

Towards Better Accuracy and Robustness with Localized Adversarial Training

Eitan Rothberg
Tingting Chen
Hao Ji

As technology and society grow increasingly dependent on computer vision, it becomes important to make sure that these technologies are secure. However, even today’s stateof-the-art classifiers are easily fooled by carefully manipulated images. The only solutions that have increased robustness against these manipulated images have come at the expense of accuracy on natural inputs. In this work, we propose a new training technique, localized adversarial training, that results in more accurate classification of both both natural and adversarial images by as much as 6. 5% and 99. 7%, respectively.

PDF Details