Junyang Chen

Jiatong Li, Zheng Chen, Kai Liu et al.

This paper provides a review of the NTIRE 2026 challenge on mobile real-world image super-resolution, highlighting the proposed solutions and the resulting outcomes. The challenge aims to recover high-resolution (HR) images from low-resolution (LR) counterparts generated through unknown degradations with a x4 scaling factor while ensuring the models remain executable on mobile devices. The objective is to develop effective and efficient network designs or solutions that achieve state-of-the-art real-world image super-resolution performance. The track of the challenge evaluates performance using a weighted combination of image quality assessment (IQA) score and speedup ratios. The competition attracted 108 registrants, with 16 teams achieving a valid score in the final ranking. This collaborative effort advances the performance of mobile real-world image super-resolution while offering an in-depth overview of the latest trends in the field.

Xin Li, Jiachao Gong, Xijun Wang et al.

This paper presents an overview of the NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models. This challenge utilizes a new short-form UGC (S-UGC) video restoration benchmark, termed KwaiVIR, which is contributed by USTC and Kuaishou Technology. It contains both synthetically distorted videos and real-world short-form UGC videos in the wild. For this edition, the released data include 200 synthetic training videos, 48 wild training videos, 11 validation videos, and 20 testing videos. The primary goal of this challenge is to establish a strong and practical benchmark for restoring short-form UGC videos under complex real-world degradations, especially in the emerging paradigm of generative-model-based S-UGC video restoration. This challenge has two tracks: (i) the primary track is a subjective track, where the evaluation is based on a user study; (ii) the second track is an objective track. These two tracks enable a comprehensive assessment of restoration quality. In total, 95 teams have registered for this competition. And 12 teams submitted valid final solutions and fact sheets for the testing phase. The submitted methods achieved strong performance on the KwaiVIR benchmark, demonstrating encouraging progress in short-form UGC video restoration in the wild.

Zheng Chen, Kai Liu, Jingkai Wang et al.

This paper presents the NTIRE 2026 image super-resolution ($\times$4) challenge, one of the associated competitions of the NTIRE 2026 Workshop at CVPR 2026. The challenge aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs generated through bicubic downsampling with a $\times$4 scaling factor. The objective is to develop effective super-resolution solutions and analyze recent advances in the field. To reflect the evolving objectives of image super-resolution, the challenge includes two tracks: (1) a restoration track, which emphasizes pixel-wise fidelity and ranks submissions based on PSNR; and (2) a perceptual track, which focuses on visual realism and evaluates results using a perceptual score. A total of 194 participants registered for the challenge, with 31 teams submitting valid entries. This report summarizes the challenge design, datasets, evaluation protocol, main results, and methods of participating teams. The challenge provides a unified benchmark and offers insights into current progress and future directions in image super-resolution.

Hui Wang, Jinghua Zhao, Yifan Yang et al.

Generative speech technologies are progressing rapidly, but evaluating the perceptual quality of synthetic speech remains a core challenge. Existing methods typically rely on scalar scores or binary decisions, which lack interpretability and generalization across tasks and languages. We present SpeechLLM-as-Judges, a new paradigm for enabling large language models (LLMs) to conduct structured and explanation-based speech quality evaluation. To support this direction, we introduce SpeechEval, a large-scale dataset containing 32,207 multilingual speech clips and 128,754 annotations spanning four tasks: quality assessment, pairwise comparison, improvement suggestion, and deepfake detection. Based on this resource, we develop SQ-LLM, a speech-quality-aware LLM trained with chain-of-thought reasoning and reward optimization to improve capability. Experimental results show that SQ-LLM delivers strong performance across tasks and languages, revealing the potential of this paradigm for advancing speech quality evaluation. The relevant code, models, and data are publicly available at https://github.com/NKU-HLT/SpeechLLM-as-Judges.

Xiang Fang, Daizong Liu, Wanlong Fang et al.

Given an untrimmed video and a sentence query, video moment retrieval using language (VMR) aims to locate a target query-relevant moment. Since the untrimmed video is overlong, almost all existing VMR methods first sparsely down-sample each untrimmed video into multiple fixed-length video clips and then conduct multi-modal interactions with the query feature and expensive clip features for reasoning, which is infeasible for long real-world videos that span hours. Since the video is downsampled into fixed-length clips, some query-related frames may be filtered out, which will blur the specific boundary of the target moment, take the adjacent irrelevant frames as new boundaries, easily leading to cross-modal misalignment and introducing both boundary-bias and reasoning-bias. To this end, in this paper, we propose an efficient approach, SpotVMR, to trim the query-relevant clip. Besides, our proposed SpotVMR can serve as plug-and-play module, which achieves efficiency for state-of-the-art VMR methods while maintaining good retrieval performance. Especially, we first design a novel clip search model that learns to identify promising video regions to search conditioned on the language query. Then, we introduce a set of low-cost semantic indexing features to capture the context of objects and interactions that suggest where to search the query-relevant moment. Also, the distillation loss is utilized to address the optimization issues arising from end-to-end joint training of the clip selector and VMR model. Extensive experiments on three challenging datasets demonstrate its effectiveness.

Zhijing Yang, Junyang Chen, Yukai Shi et al.

Image Virtual try-on aims at replacing the cloth on a personal image with a garment image (in-shop clothes), which has attracted increasing attention from the multimedia and computer vision communities. Prior methods successfully preserve the character of clothing images, however, occlusion remains a pernicious effect for realistic virtual try-on. In this work, we first present a comprehensive analysis of the occlusions and categorize them into two aspects: i) Inherent-Occlusion: the ghost of the former cloth still exists in the try-on image; ii) Acquired-Occlusion: the target cloth warps to the unreasonable body part. Based on the in-depth analysis, we find that the occlusions can be simulated by a novel semantically-guided mixup module, which can generate semantic-specific occluded images that work together with the try-on images to facilitate training a de-occlusion try-on (DOC-VTON) framework. Specifically, DOC-VTON first conducts a sharpened semantic parsing on the try-on person. Aided by semantics guidance and pose prior, various complexities of texture are selectively blending with human parts in a copy-and-paste manner. Then, the Generative Module (GM) is utilized to take charge of synthesizing the final try-on image and learning to de-occlusion jointly. In comparison to the state-of-the-art methods, DOC-VTON achieves better perceptual quality by reducing occlusion effects.

Hao Li, Zhijing Yang, Xiaobin Hong et al.

Real-world image denoising is a practical image restoration problem that aims to obtain clean images from in-the-wild noisy inputs. Recently, the Vision Transformer (ViT) has exhibited a strong ability to capture long-range dependencies, and many researchers have attempted to apply the ViT to image denoising tasks. However, a real-world image is an isolated frame that makes the ViT build long-range dependencies based on the internal patches, which divides images into patches, disarranges noise patterns and damages gradient continuity. In this article, we propose to resolve this issue by using a continuous Wavelet Sliding-Transformer that builds frequency correspondences under real-world scenes, called DnSwin. Specifically, we first extract the bottom features from noisy input images by using a convolutional neural network (CNN) encoder. The key to DnSwin is to extract high-frequency and low-frequency information from the observed features and build frequency dependencies. To this end, we propose a Wavelet Sliding-Window Transformer (WSWT) that utilizes the discrete wavelet transform (DWT), self-attention and the inverse DWT (IDWT) to extract deep features. Finally, we reconstruct the deep features into denoised images using a CNN decoder. Both quantitative and qualitative evaluations conducted on real-world denoising benchmarks demonstrate that the proposed DnSwin performs favorably against the state-of-the-art methods.

Wenting Xu, Zhenghua Xu, Junyang Chen et al.

To reduce doctors' workload, deep-learning-based automatic medical report generation has recently attracted more and more research efforts, where deep convolutional neural networks (CNNs) are employed to encode the input images, and recurrent neural networks (RNNs) are used to decode the visual features into medical reports automatically. However, these state-of-the-art methods mainly suffer from three shortcomings: (i) incomprehensive optimization, (ii) low-order and unidimensional attention mechanisms, and (iii) repeated generation. In this article, we propose a hybrid reinforced medical report generation method with m-linear attention and repetition penalty mechanism (HReMRG-MR) to overcome these problems. Specifically, a hybrid reward with different weights is employed to remedy the limitations of single-metric-based rewards. We also propose a search algorithm with linear complexity to approximate the best weight combination. Furthermore, we use m-linear attention modules to explore high-order feature interactions and to achieve multi-modal reasoning, while a repetition penalty applies penalties to repeated terms during the model's training process. Extensive experimental studies on two public datasets show that HReMRG-MR greatly outperforms the state-of-the-art baselines in terms of all metrics. We also conducted a series of ablation experiments to prove the effectiveness of all our proposed components. We also performed a reward search toy experiment to give evidence that our proposed search approach can significantly reduce the search time while approximating the best performance.

Ruizhi Wang, Xiangtao Wang, Zhenghua Xu et al.

In clinical scenarios, multiple medical images with different views are usually generated at the same time, and they have high semantic consistency. However, the existing medical report generation methods cannot exploit the rich multi-view mutual information of medical images. Therefore, in this work, we propose the first multi-view medical report generation model, called MvCo-DoT. Specifically, MvCo-DoT first propose a multi-view contrastive learning (MvCo) strategy to help the deep reinforcement learning based model utilize the consistency of multi-view inputs for better model learning. Then, to close the performance gaps of using multi-view and single-view inputs, a domain transfer network is further proposed to ensure MvCo-DoT achieve almost the same performance as multi-view inputs using only single-view inputs.Extensive experiments on the IU X-Ray public dataset show that MvCo-DoT outperforms the SOTA medical report generation baselines in all metrics.

Hexiang Zhang, Zhenghua Xu, Dan Yao et al.

Analysis of X-ray images is one of the main tools to diagnose breast cancer. The ability to quickly and accurately detect the location of masses from the huge amount of image data is the key to reducing the morbidity and mortality of breast cancer. Currently, the main factor limiting the accuracy of breast mass detection is the unequal focus on the mass boxes, leading the network to focus too much on larger masses at the expense of smaller ones. In the paper, we propose the multi-head feature pyramid module (MHFPN) to solve the problem of unbalanced focus of target boxes during feature map fusion and design a multi-head breast mass detection network (MBMDnet). Experimental studies show that, comparing to the SOTA detection baselines, our method improves by 6.58% (in AP@50) and 5.4% (in TPR@50) on the commonly used INbreast dataset, while about 6-8% improvements (in AP@20) are also observed on the public MIAS and BCS-DBT datasets.

Xiangtao Wang, Ruizhi Wang, Biao Tian et al.

Existing self-supervised learning methods based on contrastive learning and masked image modeling have demonstrated impressive performances. However, current masked image modeling methods are mainly utilized in natural images, and their applications in medical images are relatively lacking. Besides, their fixed high masking strategy limits the upper bound of conditional mutual information, and the gradient noise is considerable, making less the learned representation information. Motivated by these limitations, in this paper, we propose masked patches selection and adaptive masking strategy based self-supervised medical image segmentation method, named MPS-AMS. We leverage the masked patches selection strategy to choose masked patches with lesions to obtain more lesion representation information, and the adaptive masking strategy is utilized to help learn more mutual information and improve performance further. Extensive experiments on three public medical image segmentation datasets (BUSI, Hecktor, and Brats2018) show that our proposed method greatly outperforms the state-of-the-art self-supervised baselines.

Junyang Chen, Xiaoyu Xian, Zhijing Yang et al.

Pose transfer aims to transfer a given person into a specified posture, has recently attracted considerable attention. A typical pose transfer framework usually employs representative datasets to train a discriminative model, which is often violated by out-of-distribution (OOD) instances. Recently, test-time adaption (TTA) offers a feasible solution for OOD data by using a pre-trained model that learns essential features with self-supervision. However, those methods implicitly make an assumption that all test distributions have a unified signal that can be learned directly. In open-world conditions, the pose transfer task raises various independent signals: OOD appearance and skeleton, which need to be extracted and distributed in speciality. To address this point, we develop a SEquential Test-time Adaption (SETA). In the test-time phrase, SETA extracts and distributes external appearance texture by augmenting OOD data for self-supervised training. To make non-Euclidean similarity among different postures explicit, SETA uses the image representations derived from a person re-identification (Re-ID) model for similarity computation. By addressing implicit posture representation in the test-time sequentially, SETA greatly improves the generalization performance of current pose transfer models. In our experiment, we first show that pose transfer can be applied to open-world applications, including Tiktok reenactment and celebrity motion synthesis.

Junyang Chen, Hanjiang Lai

Zero-shot composed image retrieval (ZS-CIR), which takes a textual modification and a reference image as a query to retrieve a target image without triplet labeling, has gained more and more attention in data mining. Current ZS-CIR research mainly relies on the generalization ability of pre-trained vision-language models, e.g., CLIP. However, the pre-trained vision-language models and CIR tasks have substantial discrepancies, where the vision-language models focus on learning the similarities but CIR aims to learn the modifications of the image guided by text. In this paper, we introduce a novel unlabeled and pre-trained masked tuning approach, which reduces the gap between the pre-trained vision-language model and the downstream CIR task. First, to reduce the gap, we reformulate the contrastive learning of the vision-language model as the CIR task, where we randomly mask input image patches to generate $\langle$masked image, text, image$\rangle$ triplet from an image-text pair. Then, we propose a simple but novel pre-trained masked tuning method, which uses the text and the masked image to learn the modifications of the original image. With such a simple design, the proposed masked tuning can learn to better capture fine-grained text-guided modifications. Extensive experimental results demonstrate the significant superiority of our approach over the baseline models on four ZS-CIR datasets, including FashionIQ, CIRR, CIRCO, and GeneCIS. Our codes are available at https://github.com/Chen-Junyang-cn/PLI

Junyang Chen, Hanjiang Lai

Text-guided image retrieval is to incorporate conditional text to better capture users' intent. Traditionally, the existing methods focus on minimizing the embedding distances between the source inputs and the targeted image, using the provided triplets $\langle$source image, source text, target image$\rangle$. However, such triplet optimization may limit the learned retrieval model to capture more detailed ranking information, e.g., the triplets are one-to-one correspondences and they fail to account for many-to-many correspondences arising from semantic diversity in feedback languages and images. To capture more ranking information, we propose a novel ranking-aware uncertainty approach to model many-to-many correspondences by only using the provided triplets. We introduce uncertainty learning to learn the stochastic ranking list of features. Specifically, our approach mainly comprises three components: (1) In-sample uncertainty, which aims to capture semantic diversity using a Gaussian distribution derived from both combined and target features; (2) Cross-sample uncertainty, which further mines the ranking information from other samples' distributions; and (3) Distribution regularization, which aligns the distributional representations of source inputs and targeted image. Compared to the existing state-of-the-art methods, our proposed method achieves significant results on two public datasets for composed image retrieval.

Junyang Chen, Yuhang Jia, Hui Wang et al.

Speech editing and zero-shot Text-to-Speech (TTS) share a similar generative foundation conditioned on speech prompts, yet speech editing demands far stricter local acoustic consistency with surrounding unedited content. While prior work has shown that Supervised Fine-Tuning (SFT) enables TTS models to acquire functional editing capability, this approach remains fundamentally bottlenecked by imperfect paired editing data and coarse-grained optimization signals. To address these limitations, we propose CosyEdit2, a speech editing model built on a two-stage post-training framework that progresses from supervised editing initialization to editing-oriented Group Relative Policy Optimization (GRPO) over target-speech-free data. Extensive experiments demonstrate that CosyEdit2 not only substantially advances speech editing performance, but also unlocks better zero-shot TTS capability, revealing a deeper mutual relationship between the two tasks. Audio samples are available at https://cjy1018.github.io/CosyEdit2.

Hao Chen, Junyang Chen, Jinshan Pan et al.

Recent diffusion-based one-step methods have shown remarkable progress in the field of image super-resolution, yet they remain constrained by three critical limitations: (1) inferior fidelity performance caused by the information loss from compression encoding of low-quality (LQ) inputs; (2) insufficient region-discriminative activation of generative priors; (3) misalignment between text prompts and their corresponding semantic regions. To address these limitations, we propose CODSR, a controllable one-step diffusion network for image super-resolution. First, we propose an LQ-guided feature modulation module that leverages original uncompressed information from LQ inputs to provide high-fidelity conditioning for the diffusion process. We then develop a region-adaptive generative prior activation method to effectively enhance perceptual richness without sacrificing local structural fidelity. Finally, we employ a text-matching guidance strategy to fully harness the conditioning potential of text prompts. Extensive experiments demonstrate that CODSR achieves superior perceptual quality and competitive fidelity compared with state-of-the-art methods with efficient one-step inference.

Heqing Zou, Tianze Luo, Guiyang Xie et al.

The integration of Large Language Models (LLMs) with visual encoders has recently shown promising performance in visual understanding tasks, leveraging their inherent capability to comprehend and generate human-like text for visual reasoning. Given the diverse nature of visual data, MultiModal Large Language Models (MM-LLMs) exhibit variations in model designing and training for understanding images, short videos, and long videos. Our paper focuses on the substantial differences and unique challenges posed by long video understanding compared to static image and short video understanding. Unlike static images, short videos encompass sequential frames with both spatial and within-event temporal information, while long videos consist of multiple events with between-event and long-term temporal information. In this survey, we aim to trace and summarize the advancements of MM-LLMs from image understanding to long video understanding. We review the differences among various visual understanding tasks and highlight the challenges in long video understanding, including more fine-grained spatiotemporal details, dynamic events, and long-term dependencies. We then provide a detailed summary of the advancements in MM-LLMs in terms of model design and training methodologies for understanding long videos. Finally, we compare the performance of existing MM-LLMs on video understanding benchmarks of various lengths and discuss potential future directions for MM-LLMs in long video understanding.

Zhiqiang Kou, Junyang Chen, Xin-Qiang Cai et al.

Due to constraints on privacy, cost, and latency, on-premise deployment of small models is increasingly common. However, most practical pipelines stop at supervised fine-tuning (SFT) and fail to reach the reinforcement learning (RL) alignment stage. The main reason is that RL alignment typically requires either expensive human preference annotation or heavy reliance on high-quality reward models with large-scale API usage and ongoing engineering maintenance, both of which are ill-suited to on-premise settings. To bridge this gap, we propose a positive-unlabeled (PU) RL distillation method for on-premise small-model deployment. Without human-labeled preferences or a reward model, our method distills the teacher's preference-optimization capability from black-box generations into a locally trainable student. For each prompt, we query the teacher once to obtain an anchor response, locally sample multiple student candidates, and perform anchor-conditioned self-ranking to induce pairwise or listwise preferences, enabling a fully local training loop via direct preference optimization or group relative policy optimization. Theoretical analysis justifies that the induced preference signal by our method is order-consistent and concentrates on near-optimal candidates, supporting its stability for preference optimization. Experiments demonstrate that our method achieves consistently strong performance under a low-cost setting.

Junyang Chen, Xiangbo Lv, Zhiqiang Kou et al.

Open-vocabulary semantic segmentation (OVSS) extends traditional closed-set segmentation by enabling pixel-wise annotation for both seen and unseen categories using arbitrary textual descriptions. While existing methods leverage vision-language models (VLMs) like CLIP, their reliance on image-level pretraining often results in imprecise spatial alignment, leading to mismatched segmentations in ambiguous or cluttered scenes. However, most existing approaches lack strong object priors and region-level constraints, which can lead to object hallucination or missed detections, further degrading performance. To address these challenges, we propose LoGoSeg, an efficient single-stage framework that integrates three key innovations: (i) an object existence prior that dynamically weights relevant categories through global image-text similarity, effectively reducing hallucinations; (ii) a region-aware alignment module that establishes precise region-level visual-textual correspondences; and (iii) a dual-stream fusion mechanism that optimally combines local structural information with global semantic context. Unlike prior works, LoGoSeg eliminates the need for external mask proposals, additional backbones, or extra datasets, ensuring efficiency. Extensive experiments on six benchmarks (A-847, PC-459, A-150, PC-59, PAS-20, and PAS-20b) demonstrate its competitive performance and strong generalization in open-vocabulary settings.

Junyang Chen, Jinshan Pan, Jiangxin Dong

Faithful image super-resolution (SR) not only needs to recover images that appear realistic, similar to image generation tasks, but also requires that the restored images maintain fidelity and structural consistency with the input. To this end, we propose a simple and effective method, named FaithDiff, to fully harness the impressive power of latent diffusion models (LDMs) for faithful image SR. In contrast to existing diffusion-based SR methods that freeze the diffusion model pre-trained on high-quality images, we propose to unleash the diffusion prior to identify useful information and recover faithful structures. As there exists a significant gap between the features of degraded inputs and the noisy latent from the diffusion model, we then develop an effective alignment module to explore useful features from degraded inputs to align well with the diffusion process. Considering the indispensable roles and interplay of the encoder and diffusion model in LDMs, we jointly fine-tune them in a unified optimization framework, facilitating the encoder to extract useful features that coincide with diffusion process. Extensive experimental results demonstrate that FaithDiff outperforms state-of-the-art methods, providing high-quality and faithful SR results.

Xiaojing Chen, Dan Li, Lijun Peng et al.

The prosperous development of Artificial Intelligence-Generated Content (AIGC) has brought people's anxiety about the spread of false information on social media. Designing detectors for filtering is an effective defense method, but most detectors will be compromised by adversarial samples. Currently, most studies exposing AIGC security issues assume information on model structure and data distribution. In real applications, attackers query and interfere with models that provide services in the form of application programming interfaces (APIs), which constitutes the black-box decision-based attack paradigm. However, to the best of our knowledge, decision-based attacks on AIGC detectors remain unexplored. In this study, we propose \textbf{FBA$^2$D}: a frequency-based black-box attack method for AIGC detection to fill the research gap. Motivated by frequency-domain discrepancies between generated and real images, we develop a decision-based attack that leverages the Discrete Cosine Transform (DCT) for fine-grained spectral partitioning and selects frequency bands as query subspaces, improving both query efficiency and image quality. Moreover, attacks on AIGC detectors should mitigate initialization failures, preserve image quality, and operate under strict query budgets. To address these issues, we adopt an ``adversarial example soup'' method, averaging candidates from successive surrogate iterations and using the result as the initialization to accelerate the query-based attack. The empirical study on the Synthetic LSUN dataset and GenImage dataset demonstrate the effectiveness of our prosed method. This study shows the urgency of addressing practical AIGC security problems.

Heqing Zou, Tianze Luo, Guiyang Xie et al.

Multimodal large language models have become a popular topic in deep visual understanding due to many promising real-world applications. However, hour-long video understanding, spanning over one hour and containing tens of thousands of visual frames, remains under-explored because of 1) challenging long-term video analyses, 2) inefficient large-model approaches, and 3) lack of large-scale benchmark datasets. Among them, in this paper, we focus on building a large-scale hour-long long video benchmark, HLV-1K, designed to evaluate long video understanding models. HLV-1K comprises 1009 hour-long videos with 14,847 high-quality question answering (QA) and multi-choice question asnwering (MCQA) pairs with time-aware query and diverse annotations, covering frame-level, within-event-level, cross-event-level, and long-term reasoning tasks. We evaluate our benchmark using existing state-of-the-art methods and demonstrate its value for testing deep long video understanding capabilities at different levels and for various tasks. This includes promoting future long video understanding tasks at a granular level, such as deep understanding of long live videos, meeting recordings, and movies.

Jingcai Guo, Qihua Zhou, Ruibing Li et al.

This paper provides a novel parsimonious yet efficient design for zero-shot learning (ZSL), dubbed ParsNets, where we are interested in learning a composition of on-device friendly linear networks, each with orthogonality and low-rankness properties, to achieve equivalent or even better performance against existing deep models. Concretely, we first refactor the core module of ZSL, i.e., visual-semantics mapping function, into several base linear networks that correspond to diverse components of the semantic space, where the complex nonlinearity can be collapsed into simple local linearities. Then, to facilitate the generalization of local linearities, we construct a maximal margin geometry on the learned features by enforcing low-rank constraints on intra-class samples and high-rank constraints on inter-class samples, resulting in orthogonal subspaces for different classes and each subspace lies on a compact manifold. To enhance the model's adaptability and counterbalance over/under-fittings in ZSL, a set of sample-wise indicators is employed to select a sparse subset from these base linear networks to form a composite semantic predictor for each sample. Notably, maximal margin geometry can guarantee the diversity of features, and meanwhile, local linearities guarantee efficiency. Thus, our ParsNets can generalize better to unseen classes and can be deployed flexibly on resource-constrained devices. Theoretical explanations and extensive experiments are conducted to verify the effectiveness of the proposed method.

Yang Chen, Hui Wang, Shiyao Wang et al.

While voice technologies increasingly serve aging populations, current systems exhibit significant performance gaps due to inadequate training data capturing elderly-specific vocal characteristics like presbyphonia and dialectal variations. The limited data available on super-aged individuals in existing elderly speech datasets, coupled with overly simple recording styles and annotation dimensions, exacerbates this issue. To address the critical scarcity of speech data from individuals aged 75 and above, we introduce SeniorTalk, a carefully annotated Chinese spoken dialogue dataset. This dataset contains 55.53 hours of speech from 101 natural conversations involving 202 participants, ensuring a strategic balance across gender, region, and age. Through detailed annotation across multiple dimensions, it can support a wide range of speech tasks. We perform extensive experiments on speaker verification, speaker diarization, speech recognition, and speech editing tasks, offering crucial insights for the development of speech technologies targeting this age group.

Qin Zhang, Xiaowei Li, Jiexin Lu et al.

Open-set graph learning is a practical task that aims to classify the known class nodes and to identify unknown class samples as unknowns. Conventional node classification methods usually perform unsatisfactorily in open-set scenarios due to the complex data they encounter, such as out-of-distribution (OOD) data and in-distribution (IND) noise. OOD data are samples that do not belong to any known classes. They are outliers if they occur in training (OOD noise), and open-set samples if they occur in testing. IND noise are training samples which are assigned incorrect labels. The existence of IND noise and OOD noise is prevalent, which usually cause the ambiguity problem, including the intra-class variety problem and the inter-class confusion problem. Thus, to explore robust open-set learning methods is necessary and difficult, and it becomes even more difficult for non-IID graph data.To this end, we propose a unified framework named ROG$_{PL}$ to achieve robust open-set learning on complex noisy graph data, by introducing prototype learning. In specific, ROG$_{PL}$ consists of two modules, i.e., denoising via label propagation and open-set prototype learning via regions. The first module corrects noisy labels through similarity-based label propagation and removes low-confidence samples, to solve the intra-class variety problem caused by noise. The second module learns open-set prototypes for each known class via non-overlapped regions and remains both interior and border prototypes to remedy the inter-class confusion problem.The two modules are iteratively updated under the constraints of classification loss and prototype diversity loss. To the best of our knowledge, the proposed ROG$_{PL}$ is the first robust open-set node classification method for graph data with complex noise.

Junyang Chen, Jiangxin Dong, Long Sun et al.

We present STCDiT, a video super-resolution framework built upon a pre-trained video diffusion model, aiming to restore structurally faithful and temporally stable videos from degraded inputs, even under complex camera motions. The main challenges lie in maintaining temporal stability during reconstruction and preserving structural fidelity during generation. To address these challenges, we first develop a motion-aware VAE reconstruction method that performs segment-wise reconstruction, with each segment clip exhibiting uniform motion characteristic, thereby effectively handling videos with complex camera motions. Moreover, we observe that the first-frame latent extracted by the VAE encoder in each clip, termed the anchor-frame latent, remains unaffected by temporal compression and retains richer spatial structural information than subsequent frame latents. We further develop an anchor-frame guidance approach that leverages structural information from anchor frames to constrain the generation process and improve structural fidelity of video features. Coupling these two designs enables the video diffusion model to achieve high-quality video super-resolution. Extensive experiments show that STCDiT outperforms state-of-the-art methods in terms of structural fidelity and temporal consistency.

Zhiqiang Kou, Junyang Chen, Xin-Qiang Cai et al.

Large language models (LLMs) have achieved impressive results across a range of natural language processing tasks, but their potential to generate harmful content has raised serious safety concerns. Current toxicity detectors primarily rely on single-label benchmarks, which cannot adequately capture the inherently ambiguous and multi-dimensional nature of real-world toxic prompts. This limitation results in biased evaluations, including missed toxic detections and false positives, undermining the reliability of existing detectors. Additionally, gathering comprehensive multi-label annotations across fine-grained toxicity categories is prohibitively costly, further hindering effective evaluation and development. To tackle these issues, we introduce three novel multi-label benchmarks for toxicity detection: \textbf{Q-A-MLL}, \textbf{R-A-MLL}, and \textbf{H-X-MLL}, derived from public toxicity datasets and annotated according to a detailed 15-category taxonomy. We further provide a theoretical proof that, on our released datasets, training with pseudo-labels yields better performance than directly learning from single-label supervision. In addition, we develop a pseudo-label-based toxicity detection method. Extensive experimental results show that our approach significantly surpasses advanced baselines, including GPT-4o and DeepSeek, thus enabling more accurate and reliable evaluation of multi-label toxicity in LLM-generated content.

Wenqing Wang, Muhammad Asif Ali, Ali Shoker et al.

Human preferences are diverse and dynamic, shaped by regional, cultural, and social factors. Existing alignment methods like Direct Preference Optimization (DPO) and its variants often default to majority views, overlooking minority opinions and failing to capture latent user intentions in prompts. To address these limitations, we introduce \underline{\textbf{A}}daptive \textbf{\underline{I}}ntent-driven \textbf{\underline{P}}reference \textbf{\underline{O}}ptimization (\textbf{A-IPO}). Specifically,A-IPO introduces an intention module that infers the latent intent behind each user prompt and explicitly incorporates this inferred intent into the reward function, encouraging stronger alignment between the preferred model's responses and the user's underlying intentions. We demonstrate, both theoretically and empirically, that incorporating an intention--response similarity term increases the preference margin (by a positive shift of $λ\,Δ\mathrm{sim}$ in the log-odds), resulting in clearer separation between preferred and dispreferred responses compared to DPO. For evaluation, we introduce two new benchmarks, Real-pref, Attack-pref along with an extended version of an existing dataset, GlobalOpinionQA-Ext, to assess real-world and adversarial preference alignment. Through explicit modeling of diverse user intents,A-IPO facilitates pluralistic preference optimization while simultaneously enhancing adversarial robustness in preference alignment. Comprehensive empirical evaluation demonstrates that A-IPO consistently surpasses existing baselines, yielding substantial improvements across key metrics: up to +24.8 win-rate and +45.6 Response-Intention Consistency on Real-pref; up to +38.6 Response Similarity and +52.2 Defense Success Rate on Attack-pref; and up to +54.6 Intention Consistency Score on GlobalOpinionQA-Ext.

Junyang Chen, Yang Lu, Mengke Li et al.

Clustering complex data in the form of attributed graphs has attracted increasing attention, where powerful graph representation is a critical prerequisite. However, the well-known Over-Smoothing (OS) effect makes Graph Convolutional Networks tend to homogenize the representation of graph nodes, while the existing OS solutions focus on alleviating the homogeneity of nodes' embeddings from the aspect of graph topology information, which is inconsistent with the attributed graph clustering objective. Therefore, we introduce hyper-complex space with powerful quaternion feature transformation to enhance the representation learning of the attributes. A generalized \textbf{Hy}per-complex space \textbf{Re}present\textbf{a}tion \textbf{L}earning (\textbf{HyReaL}) model is designed to: 1) bridge arbitrary dimensional attributes to the well-developed quaternion algebra with four parts, and 2) connect the learned representations to more generalized clustering objective without being restricted to a given number of clusters $k$. The novel introduction of quaternion benefits attributed graph clustering from two aspects: 1) enhanced attribute coupling learning capability allows complex attribute information to be sufficiently exploited in clustering, and 2) stronger learning capability makes it unnecessary to stack too many graph convolution layers, naturally alleviating the OS problem. It turns out that the node representations learned by HyReaL are more discriminative and widely suit downstream clustering with different $k$s. Extensive experiments including significance tests, ablation studies, qualitative results, etc., show the superiority of HyReaL.

Ge Fan, Chaoyun Zhang, Kai Wang et al.

The multiplayer online battle arena (MOBA) genre has gained significant popularity and economic success, attracting considerable research interest within the Human-Computer Interaction community. Enhancing the gaming experience requires a deep understanding of player behavior, and a crucial aspect of MOBA games is matchmaking, which aims to assemble teams of comparable skill levels. However, existing matchmaking systems often neglect important factors such as players' position preferences and team assignment, resulting in imbalanced matches and reduced player satisfaction. To address these limitations, this paper proposes a novel framework called CUPID, which introduces a novel process called ``re-matchmaking'' to optimize team and position assignments to improve both fairness and player satisfaction. CUPID incorporates a pre-filtering step to ensure a minimum level of matchmaking quality, followed by a pre-match win-rate prediction model that evaluates the fairness of potential assignments. By simultaneously considering players' position satisfaction and game fairness, CUPID aims to provide an enhanced matchmaking experience. Extensive experiments were conducted on two large-scale, real-world MOBA datasets to validate the effectiveness of CUPID. The results surpass all existing state-of-the-art baselines, with an average relative improvement of 7.18% in terms of win prediction accuracy. Furthermore, CUPID has been successfully deployed in a popular online mobile MOBA game. The deployment resulted in significant improvements in match fairness and player satisfaction, as evidenced by critical Human-Computer Interaction (HCI) metrics covering usability, accessibility, and engagement, observed through A/B testing. To the best of our knowledge, CUPID is the first re-matchmaking system designed specifically for large-scale MOBA games.

Wei Wang, Baopu Li, Shuhui Yang et al.

Domain adaptation has received a lot of attention in recent years, and many algorithms have been proposed with impressive progress. However, it is still not fully explored concerning the joint probability distribution (P(X, Y)) distance for this problem, since its empirical estimation derived from the maximum mean discrepancy (joint maximum mean discrepancy, JMMD) will involve complex tensor-product operator that is hard to manipulate. To solve this issue, this paper theoretically derives a unified form of JMMD that is easy to optimize, and proves that the marginal, class conditional and weighted class conditional probability distribution distances are our special cases with different label kernels, among which the weighted class conditional one not only can realize feature alignment across domains in the category level, but also deal with imbalance dataset using the class prior probabilities. From the revealed unified JMMD, we illustrate that JMMD degrades the feature-label dependence (discriminability) that benefits to classification, and it is sensitive to the label distribution shift when the label kernel is the weighted class conditional one. Therefore, we leverage Hilbert Schmidt independence criterion and propose a novel MMD matrix to promote the dependence, and devise a novel label kernel that is robust to label distribution shift. Finally, we conduct extensive experiments on several cross-domain datasets to demonstrate the validity and effectiveness of the revealed theoretical results.

Chang Qi, Junyang Chen, Guizhi Xu et al.

Recently deep learning methods, in particular, convolutional neural networks (CNNs), have led to a massive breakthrough in the range of computer vision. Also, the large-scale annotated dataset is the essential key to a successful training procedure. However, it is a huge challenge to get such datasets in the medical domain. Towards this, we present a data augmentation method for generating synthetic medical images using cycle-consistency Generative Adversarial Networks (GANs). We add semi-supervised attention modules to generate images with convincing details. We treat tumor images and normal images as two domains. The proposed GANs-based model can generate a tumor image from a normal image, and in turn, it can also generate a normal image from a tumor image. Furthermore, we show that generated medical images can be used for improving the performance of ResNet18 for medical image classification. Our model is applied to three limited datasets of tumor MRI images. We first generate MRI images on limited datasets, then we trained three popular classification models to get the best model for tumor classification. Finally, we train the classification model using real images with classic data augmentation methods and classification models using synthetic images. The classification results between those trained models showed that the proposed SAG-GAN data augmentation method can boost Accuracy and AUC compare with classic data augmentation methods. We believe the proposed data augmentation method can apply to other medical image domains, and improve the accuracy of computer-assisted diagnosis.

Bo Wang, Lei Wang, Junyang Chen et al.

Deep learning-based medical image segmentation technology aims at automatic recognizing and annotating objects on the medical image. Non-local attention and feature learning by multi-scale methods are widely used to model network, which drives progress in medical image segmentation. However, those attention mechanism methods have weakly non-local receptive fields' strengthened connection for small objects in medical images. Then, the features of important small objects in abstract or coarse feature maps may be deserted, which leads to unsatisfactory performance. Moreover, the existing multi-scale methods only simply focus on different sizes of view, whose sparse multi-scale features collected are not abundant enough for small objects segmentation. In this work, a multi-dimensional attention segmentation model with cascade multi-scale convolution is proposed to predict accurate segmentation for small objects in medical images. As the weight function, multi-dimensional attention modules provide coefficient modification for significant/informative small objects features. Furthermore, The cascade multi-scale convolution modules in each skip-connection path are exploited to capture multi-scale features in different semantic depth. The proposed method is evaluated on three datasets: KiTS19, Pancreas CT of Decathlon-10, and MICCAI 2018 LiTS Challenge, demonstrating better segmentation performances than the state-of-the-art baselines.

Di Yuan, Junyang Chen, Zhenghua Xu et al.

Because the expansion path of U-Net may ignore the characteristics of small targets, intermediate supervision mechanism is proposed. The original mask is also entered into the network as a label for intermediate output. However, U-Net is mainly engaged in segmentation, and the extracted features are also targeted at segmentation location information, and the input and output are different. The label we need is that the input and output are both original masks, which is more similar to the refactoring process, so we propose another intermediate supervision mechanism. However, the features extracted by the contraction path of this intermediate monitoring mechanism are not necessarily consistent. For example, U-Net's contraction path extracts transverse features, while auto-encoder extracts longitudinal features, which may cause the output of the expansion path to be inconsistent with the label. Therefore, we put forward the intermediate supervision mechanism of shared-weight decoder module. Although the intermediate supervision mechanism improves the segmentation accuracy, the training time is too long due to the extra input and multiple loss functions. For one of these problems, we have introduced tied-weight decoder. To reduce the redundancy of the model, we combine shared-weight decoder module with tied-weight decoder module.

Cong Wang, Yutong Wu, Zhixun Su et al.

In the field of multimedia, single image deraining is a basic pre-processing work, which can greatly improve the visual effect of subsequent high-level tasks in rainy conditions. In this paper, we propose an effective algorithm, called JDNet, to solve the single image deraining problem and conduct the segmentation and detection task for applications. Specifically, considering the important information on multi-scale features, we propose a Scale-Aggregation module to learn the features with different scales. Simultaneously, Self-Attention module is introduced to match or outperform their convolutional counterparts, which allows the feature aggregation to adapt to each channel. Furthermore, to improve the basic convolutional feature transformation process of Convolutional Neural Networks (CNNs), Self-Calibrated convolution is applied to build long-range spatial and inter-channel dependencies around each spatial location that explicitly expand fields-of-view of each convolutional layer through internal communications and hence enriches the output features. By designing the Scale-Aggregation and Self-Attention modules with Self-Calibrated convolution skillfully, the proposed model has better deraining results both on real-world and synthetic datasets. Extensive experiments are conducted to demonstrate the superiority of our method compared with state-of-the-art methods. The source code will be available at \url{https://supercong94.wixsite.com/supercong94}.

Cong Wang, Xiaoying Xing, Zhixun Su et al.

Rain removal is an important but challenging computer vision task as rain streaks can severely degrade the visibility of images that may make other visions or multimedia tasks fail to work. Previous works mainly focused on feature extraction and processing or neural network structure, while the current rain removal methods can already achieve remarkable results, training based on single network structure without considering the cross-scale relationship may cause information drop-out. In this paper, we explore the cross-scale manner between networks and inner-scale fusion operation to solve the image rain removal task. Specifically, to learn features with different scales, we propose a multi-sub-networks structure, where these sub-networks are fused via a crossscale manner by Gate Recurrent Unit to inner-learn and make full use of information at different scales in these sub-networks. Further, we design an inner-scale connection block to utilize the multi-scale information and features fusion way between different scales to improve rain representation ability and we introduce the dense block with skip connection to inner-connect these blocks. Experimental results on both synthetic and real-world datasets have demonstrated the superiority of our proposed method, which outperforms over the state-of-the-art methods. The source code will be available at https://supercong94.wixsite.com/supercong94.

Andreas Lugmayr, Martin Danelljan, Radu Timofte et al.

This paper reviews the NTIRE 2020 challenge on real world super-resolution. It focuses on the participating methods and final results. The challenge addresses the real world setting, where paired true high and low-resolution images are unavailable. For training, only one set of source input images is therefore provided along with a set of unpaired high-quality target images. In Track 1: Image Processing artifacts, the aim is to super-resolve images with synthetically generated image processing artifacts. This allows for quantitative benchmarking of the approaches \wrt a ground-truth image. In Track 2: Smartphone Images, real low-quality smart phone images have to be super-resolved. In both tracks, the ultimate goal is to achieve the best perceptual quality, evaluated using a human study. This is the second challenge on the subject, following AIM 2019, targeting to advance the state-of-the-art in super-resolution. To measure the performance we use the benchmark protocol from AIM 2019. In total 22 teams competed in the final testing phase, demonstrating new and innovative solutions to the problem.

Xiaoran Cai, Xiaopeng Mo, Junyang Chen et al.

Mobile edge learning is an emerging technique that enables distributed edge devices to collaborate in training shared machine learning models by exploiting their local data samples and communication and computation resources. To deal with the straggler dilemma issue faced in this technique, this paper proposes a new device to device enabled data sharing approach, in which different edge devices share their data samples among each other over communication links, in order to properly adjust their computation loads for increasing the training speed. Under this setup, we optimize the radio resource allocation for both data sharing and distributed training, with the objective of minimizing the total training delay under fixed numbers of local and global iterations. Numerical results show that the proposed data sharing design significantly reduces the training delay, and also enhances the training accuracy when the data samples are non independent and identically distributed among edge devices.