arXiv subjects

Xinger Li

Publications and source records attributed to Xinger Li.

4 recordsLinked to original sources

arXiv2026

NTIRE 2026 Rip Current Detection and Segmentation (RipDetSeg) Challenge Report

This report presents the NTIRE 2026 Rip Current Detection and Segmentation (RipDetSeg) Challenge, which targets automatic rip current understanding in images. Rip currents are hazardous nearshore flows that cause many beach-related fatalities worldwide, yet remain difficult to identify because their visual appearance varies substantially across beaches, viewpoints, and sea states. To advance research on this safety-critical problem, the challenge builds on the RipVIS benchmark, evaluating both detection and segmentation. The dataset is diverse, sourced from more than $10$ countries, with $4$ camera orientations and diverse beach and sea conditions. This report describes the dataset, challenge protocol, evaluation methodology, final results, and summarizes the main insights from the submitted methods. The challenge attracted $159$ registered participants and produced $9$ valid test submissions across the two tasks. Final rankings are based on a composite score that combines $F_1[50]$, $F_2[50]$, $F_1[40\!:\!95]$, and $F_2[40\!:\!95]$. Most participant solutions relied on pretrained models, combined with strong augmentation and post-processing design. These results suggest that rip current understanding benefits strongly from the robust general-purpose vision models' progress, while leaving ample room for future methods tailored to their unique visual structure.

cs.CV↗

arXiv2025

Fitting Different Interactive Information: Joint Classification of Emotion and Intention

This paper is the first-place solution for ICASSP MEIJU@2025 Track I, which focuses on low-resource multimodal emotion and intention recognition. How to effectively utilize a large amount of unlabeled data, while ensuring the mutual promotion of different difficulty levels tasks in the interaction stage, these two points become the key to the competition. In this paper, pseudo-label labeling is carried out on the model trained with labeled data, and samples with high confidence and their labels are selected to alleviate the problem of low resources. At the same time, the characteristic of easy represented ability of intention recognition found in the experiment is used to make mutually promote with emotion recognition under different attention heads, and higher performance of intention recognition is achieved through fusion. Finally, under the refined processing data, we achieve the score of 0.5532 in the Test set, and win the championship of the track.

cs.CV↗

arXiv2024

The Solution for The PST-KDD-2024 OAG-Challenge

In this paper, we introduce the second-place solution in the KDD-2024 OAG-Challenge paper source tracing track. Our solution is mainly based on two methods, BERT and GCN, and combines the reasoning results of BERT and GCN in the final submission to achieve complementary performance. In the BERT solution, we focus on processing the fragments that appear in the references of the paper, and use a variety of operations to reduce the redundant interference in the fragments, so that the information received by BERT is more refined. In the GCN solution, we map information such as paper fragments, abstracts, and titles to a high-dimensional semantic space through an embedding model, and try to build edges between titles, abstracts, and fragments to integrate contextual relationships for judgment. In the end, our solution achieved a remarkable score of 0.47691 in the competition.

cs.CL↗

arXiv2024

Solution for Authenticity Identification of Typical Target Remote Sensing Images

In this paper, we propose a basic RGB single-mode model based on weakly supervised training under pseudo labels, which performs high-precision authenticity identification under multi-scene typical target remote sensing images. Due to the imprecision of Mask generation, we divide the task into two sub-tasks: generating pseudo-mask and fine-tuning model based on generated Masks. In generating pseudo masks, we use MM-Fusion as the base model to generate masks for large objects such as planes and ships. By manually calibrating the Mask of a small object such as a car, a highly accurate pseudo-mask is obtained. For the task of fine-tuning models based on generating masks, we use the WSCL model as the base model. It is worth noting that due to the difference between the generated pseudo-Masks and the real Masks, we discard the image feature extractors such as SRM and Noiseprint++ in WSCL, and select the unscaled original image for training alone, which greatly ensures the match between the image and the original label. The final trained model achieved a score of 90.7702 on the test set.

eess.IV↗