Author name cluster

Liwei 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.

4 papers

1 author row

AAAI Conference 2025 Conference Paper

Granularity-Adaptive Spatial Evidence Tokenization for Video Question Answering

Hao Jiang
Yang Jin
Zhicheng Sun
Kun Xu
Liwei Chen
Yang Song
Kun Gai
Yadong Mu

Video question answering plays a vital role in computer vision, and recent advances in large language models have further propelled the development of this field. However, existing video question answering techniques often face limitations in grasping fine-grained video content in spatial dimensions. It mainly stems from the fixed and low-resolution input of video frames. While some approaches using high-resolution inputs partially alleviate this problem, they introduce excessive computational burdens by encoding the entire high-resolution image. In this work, we propose a granularity-adaptive spatial evidence tokenization model for video question answering. Our method introduces multi-granular visual tokenization in the spatial dimension to produce video tokens at various granularities based on the question. It highlights spatially activated patches at low resolutions through a granularity weighting module and then adaptively encodes these activated patches at high resolution for detail supplementation. To mitigate the computational overhead associated with high-resolution frame encoding, a masking and acceleration module is developed for efficient visual tokenization. Moreover, a granularity compression module is designed to dynamically select and compress visual tokens of varying granularities based on questions. We conduct extensive experiments on 11 mainstream video question answering datasets and the experimental results demonstrate the effectiveness of our proposed method.

PDF Details DOI

EAAI Journal 2024 Journal Article

Real-time defect detection of saw chains on automatic assembly lines based on residual networks and knowledge coding

Fubao Zhang
Ting Wu
Susu Liu
Yu Zhu
Liwei Chen
Toshiaki Natsuki

The use of machine vision methods has rapidly developed for detecting product defects, but it remains challenging to identify shape and color defects as well as the assembly relationship of parts due to occlusion between components and changes in assembly structures. This paper proposed a method for detecting saw chain assembly defects based on residual networks and knowledge coding to achieve parts segmentation and identification of assembly defects. Firstly, we design an adaptive segmentation algorithm for saw chain parts, which uses the Hough transform to locate rivets and completes the image segmentation based on the inherent assembly features between parts. Secondly, A trained ResNet (Residual Network) based deep learning model was used to identify the individual defects of saw chain parts, in which the transfer learning method was used to improve the detection speed of individual defects. Finally, a parallel inference method based on a knowledge encoding matrix is proposed for detecting part defects and constructing a sparse matrix to locate assembly defects. Evaluating the proposed method in building a saw chain testing platform. Results show that the proposed method can achieve real-time and high-precision detection requirements in different application scenarios. The detection accuracy on individual and assembly defects reaches 94. 2% and 89. 2%, respectively, which is better than the current state-of-the-art object detection models. Assembly defect detection methods are an important reference for inspecting other types of simple assemblies in the industry.

Details DOI

NeurIPS Conference 2024 Conference Paper

RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance

Zhicheng Sun
Zhenhao Yang
Yang Jin
Haozhe Chi
Kun Xu
Liwei Chen
Hao Jiang
Yang Song

Customizing diffusion models to generate identity-preserving images from user-provided reference images is an intriguing new problem. The prevalent approaches typically require training on extensive domain-specific images to achieve identity preservation, which lacks flexibility across different use cases. To address this issue, we exploit classifier guidance, a training-free technique that steers diffusion models using an existing classifier, for personalized image generation. Our study shows that based on a recent rectified flow framework, the major limitation of vanilla classifier guidance in requiring a special classifier can be resolved with a simple fixed-point solution, allowing flexible personalization with off-the-shelf image discriminators. Moreover, its solving procedure proves to be stable when anchored to a reference flow trajectory, with a convergence guarantee. The derived method is implemented on rectified flow with different off-the-shelf image discriminators, delivering advantageous personalization results for human faces, live subjects, and certain objects. Code is available at https: //github. com/feifeiobama/RectifID.

PDF Details DOI

AIJ Journal 2018 Journal Article

Encoding implicit relation requirements for relation extraction: A joint inference approach

Liwei Chen
Yansong Feng
Songfang Huang
Bingfeng Luo
Dongyan Zhao

Relation extraction is the task of identifying predefined relationship between entities, and plays an essential role in information extraction, knowledge base construction, question answering and so on. Most existing relation extractors make predictions for each entity pair locally and individually, while ignoring implicit global clues available across different entity pairs and in the knowledge base, which often leads to conflicts among local predictions from different entity pairs. This paper proposes a joint inference framework that employs such global clues to resolve disagreements among local predictions. We exploit two kinds of clues to generate constraints which can capture the implicit type and cardinality requirements of a relation. Those constraints can be examined in either hard style or soft style, both of which can be effectively explored in an integer linear program formulation. Experimental results on both English and Chinese datasets show that our proposed framework can effectively utilize those two categories of global clues and resolve the disagreements among local predictions, thus improve various relation extractors when such clues are applicable to the datasets. Our experiments also indicate that the clues learnt automatically from existing knowledge bases perform comparably to or better than those refined by human.

Details DOI