Arrow Research search

Author name cluster

Yiping 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
2 author rows

Possible papers

7

AAAI Conference 2026 Conference Paper

SGS-3D: High-Fidelity 3D Instance Segmentation via Reliable Semantic Mask Splitting and Growing

  • Chaolei Wang
  • Yang Luo
  • Jing Du
  • Siyu Chen
  • Yiping Chen
  • Ting Han

Accurate 3D instance segmentation is crucial for high-quality scene understanding in the 3D vision domain. However, 3D instance segmentation based on 2D-to-3D lifting approaches struggle to produce precise instance-level segmentation, due to accumulated errors introduced during the lifting process from ambiguous semantic guidance and insufficient depth constraints. To tackle these challenges, we propose Splitting and Growing reliable Semantic mask for high-fidelity 3D instance segmentation (SGS-3D), a novel "split-then-grow" framework that first purifies and splits ambiguous lifted masks using geometric primitives, and then grows them into complete instances within the scene. Unlike existing approaches that directly rely on raw lifted masks and sacrifice segmentation accuracy, SGS-3D serves as a training-free refinement method that jointly fuses semantic and geometric information, enabling effective cooperation between the two levels of representation. Specifically, for semantic guidance, we introduce a mask filtering strategy that leverages the co-occurrence of 3D geometry primitives to identify and remove ambiguous masks, thereby ensuring more reliable semantic consistency with the 3D object instances. For the geometric refinement, we construct fine-grained object instances by exploiting both spatial continuity and high-level features, particularly in the case of semantic ambiguity between distinct objects. Experimental results on ScanNet200, ScanNet++, and KITTI-360 demonstrate that SGS-3D substantially improves segmentation accuracy and robustness against inaccurate masks from pre-trained models, yielding high-fidelity object instances while maintaining strong generalization across diverse indoor and outdoor environments.

PDF Details DOI

ICLR Conference 2025 Conference Paper

LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models

  • Junyan Ye
  • Baichuan Zhou
  • Zilong Huang
  • Junan Zhang
  • Tianyi Bai
  • Hengrui Kang
  • Jun He
  • Honglin Lin

With the rapid development of AI-generated content, the future internet may be inundated with synthetic data, making the discrimination of authentic and credible multimodal data increasingly challenging. Synthetic data detection has thus garnered widespread attention, and the performance of large multimodal models (LMMs) in this task has attracted significant interest. LMMs can provide natural language explanations for their authenticity judgments, enhancing the explainability of synthetic content detection. Simultaneously, the task of distinguishing between real and synthetic data effectively tests the perception, knowledge, and reasoning capabilities of LMMs. In response, we introduce LOKI, a novel benchmark designed to evaluate the ability of LMMs to detect synthetic data across multiple modalities. LOKI encompasses video, image, 3D, text, and audio modalities, comprising 18K carefully curated questions across 26 subcategories with clear difficulty levels. The benchmark includes coarse-grained judgment and multiple-choice questions, as well as fine-grained anomaly selection and explanation tasks, allowing for a comprehensive analysis of LMMs. We evaluated 22 open-source LMMs and 6 closed-source models on LOKI, highlighting their potential as synthetic data detectors and also revealing some limitations in the development of LMM capabilities. More information about LOKI can be found at https://opendatalab.github.io/LOKI/.

Details

IJCAI Conference 2021 Conference Paper

Direction-aware Feature-level Frequency Decomposition for Single Image Deraining

  • Sen Deng
  • Yidan Feng
  • Mingqiang Wei
  • Haoran Xie
  • Yiping Chen
  • Jonathan Li
  • Xiao-Ping Zhang
  • Jing Qin

We present a novel direction-aware feature-level frequency decomposition network for single image deraining. Compared with existing solutions, the proposed network has three compelling characteristics. First, unlike previous algorithms, we propose to perform frequency decomposition at feature-level instead of image-level, allowing both low-frequency maps containing structures and high-frequency maps containing details to be continuously refined during the training procedure. Second, we further establish communication channels between low-frequency maps and high-frequency maps to interactively capture structures from high-frequency maps and add them back to low-frequency maps and, simultaneously, extract details from low-frequency maps and send them back to high-frequency maps, thereby removing rain streaks while preserving more delicate features in the input image. Third, different from existing algorithms using convolutional filters consistent in all directions, we propose a direction-aware filter to capture the direction of rain streaks in order to more effectively and thoroughly purge the input images of rain streaks. We extensively evaluate the proposed approach in three representative datasets and experimental results corroborate our approach consistently outperforms state-of-the-art deraining algorithms.

PDF Details DOI

AAAI Conference 2019 Short Paper

Geometric Multi-Model Fitting by Deep Reinforcement Learning

  • Zongliang Zhang
  • Hongbin Zeng
  • Jonathan Li
  • Yiping Chen
  • Chenhui Yang
  • Cheng Wang

This paper deals with the geometric multi-model fitting from noisy, unstructured point set data (e. g. , laser scanned point clouds). We formulate multi-model fitting problem as a sequential decision making process. We then use a deep reinforcement learning algorithm to learn the optimal decisions towards the best fitting result. In this paper, we have compared our method against the state-of-the-art on simulated data. The results demonstrated that our approach significantly reduced the number of fitting iterations.

PDF Details

YNIMG Journal 2002 Journal Article

Effects of Word Form on Brain Processing of Written Chinese

  • Shimin Fu
  • Yiping Chen
  • Stephen Smith
  • Susan Iversen
  • P.M. Matthews

Both logographic characters and alphabetic pinyins can be used to write words in Chinese. Here we use fMRI to address the question of whether the written form affects brain processing of a word. Fifteen healthy, right-handed, native Chinese-reading volunteers participated in our study and were asked to read silently either Chinese characters (8 subjects) or pinyins (7 subjects). The stimulus presentation rate was varied for both tasks to allow us to identify brain regions with word-load-dependent activation. Rate effects (fast minus slow presentations) for Chinese character reading were observed in striate and extrastriate visual cortex, superior parietal lobule, left posterior middle temporal gyrus, bilateral inferior temporal gyri, and bilateral superior frontal gyri. Rate effects for pinyin reading were observed in bilateral fusiform, lingual, and middle occipital gyri, bilateral superior parietal lobule/precuneus, left inferior parietal lobule, bilateral inferior temporal gyrus, left middle temporal gyrus, and left superior temporal gyrus. These results demonstrate that common regions of the brain are involved in reading both Chinese characters and pinyins, activated apparently independently of the surface form of the word. There also appear to be brain regions in which activation is dependent on word form. However, it is unlikely that these are entirely specific for a given word form; their activation more likely reflects relative functional specializations within broader networks for processing written language.

Details DOI