Li Jia

Tianshu Yu, Changqun Xia, Jia Li

Video portrait segmentation (VPS), aiming at segmenting prominent foreground portraits from video frames, has received much attention in recent years. However, simplicity of existing VPS datasets leads to a limitation on extensive research of the task. In this work, we propose a new intricate large-scale Multi-scene Video Portrait Segmentation dataset MVPS consisting of 101 video clips in 7 scenario categories, in which 10,843 sampled frames are finely annotated at pixel level. The dataset has diverse scenes and complicated background environments, which is the most complex dataset in VPS to our best knowledge. Through the observation of a large number of videos with portraits during dataset construction, we find that due to the joint structure of human body, motion of portraits is part-associated, which leads that different parts are relatively independent in motion. That is, motion of different parts of the portraits is imbalanced. Towards this imbalance, an intuitive and reasonable idea is that different motion states in portraits can be better exploited by decoupling the portraits into parts. To achieve this, we propose a Part-Decoupling Network (PDNet) for video portrait segmentation. Specifically, an Inter-frame Part-Discriminated Attention (IPDA) module is proposed which unsupervisedly segments portrait into parts and utilizes different attentiveness on discriminative features specified to each different part. In this way, appropriate attention can be imposed to portrait parts with imbalanced motion to extract part-discriminated correlations, so that the portraits can be segmented more accurately. Experimental results demonstrate that our method achieves leading performance with the comparison to state-of-the-art methods.

Huanyu Liu, Jia Li, Chang Yu et al. · pku

Reinforcement learning with verifiable reward (RLVR) has become a promising paradigm for post-training large language models (LLMs) to improve their reasoning capability. However, when the rollout accuracy is low on hard problems, the reward becomes sparse, limiting learning efficiency and causing exploration bottlenecks. Existing approaches either rely on teacher models for distillation or filter out difficult problems, which limits scalability or restricts reasoning improvement through exploration. We propose EvoCoT, a self-evolving curriculum learning framework based on two-stage chain-of-thought (CoT) reasoning optimization. EvoCoT constrains the exploration space by self-generating and verifying CoT trajectories, then gradually shortens CoT steps to expand the space in a controlled way. The framework enables LLMs to stably learn from initially unsolved hard problems under sparse rewards. We apply EvoCoT to multiple LLM families, including Qwen, DeepSeek, and Llama. Experiments show that EvoCoT enables LLMs to solve previously unsolved problems, improves reasoning capability without external CoT supervision, and is compatible with various RL fine-tuning methods. We release the source code to support future research.

Jinming Su, Changqun Xia, Jia Li

Recently, general salient object detection (SOD) has made great progress with the rapid development of deep neural networks. However, task-aware SOD has hardly been studied due to the lack of task-specific datasets. In this paper, we construct a driving task-oriented dataset where pixel-level masks of salient objects have been annotated. Comparing with general SOD datasets, we find that the cross-domain knowledge difference and task-specific scene gap are two main challenges to focus the salient objects when driving. Inspired by these findings, we proposed a baseline model for the driving task-aware SOD via a knowledge transfer convolutional neural network. In this network, we construct an attentionbased knowledge transfer module to make up the knowledge difference. In addition, an efficient boundary-aware feature decoding module is introduced to perform fine feature decoding for objects in the complex task-specific scenes. The whole network integrates the knowledge transfer and feature decoding modules in a progressive manner. Experiments show that the proposed dataset is very challenging, and the proposed method outperforms 12 state-of-the-art methods on the dataset, which facilitates the development of task-aware SOD.

Kui Fu, Jia Li, Lin Ma et al.

The small objects in images and videos are usually not independent individuals. Instead, they more or less present some semantic and spatial layout relationships with each other. Modeling and inferring such intrinsic relationships can thereby be beneficial for small object detection. In this paper, we propose a novel context reasoning approach for small object detection which models and infers the intrinsic semantic and spatial layout relationships between objects. Specifically, we first construct a semantic module to model the sparse semantic relationships based on the initial regional features, and a spatial layout module to model the sparse spatial layout relationships based on their position and shape information, respectively. Both of them are then fed into a context reasoning module for integrating the contextual information with respect to the objects and their relationships, which is further fused with the original regional visual features for classification and regression. Experimental results reveal that the proposed approach can effectively boost the small object detection performance.

Jia Li, Daowei Li, Kui Fu et al.

Visual attention prediction is a classic problem that seems to be well addressed in the deep learning era. One compelling concern, however, gradually arise along with the rapidly growing performance scores over existing visual attention datasets: do existing deep models really capture the inherent mechanism of human visual attention? To address this concern, this paper proposes a new dataset, named VASUN, that records the free-viewing human attention on solar images. Different from previous datasets, images in VASUN contain many irregular visual patterns that existing deep models have never seen. By benchmarking existing models on VASUN, we find the performances of many state-of-the-art deep models drop remarkably, while many classic shallow models perform impressively. From these results, we find that the significant performance advance of existing deep attention models may come from their capabilities of memorizing and predicting the occurrence of some specific visual patterns other than learning the inherent mechanism of human visual attention. In addition, we also train several baseline models on VASUN to demonstrate the feasibility and key issues of predicting visual attention on the sun. These baseline models, together with the proposed dataset, can be used to revisit the problem of visual attention prediction from a novel perspective that are complementary to existing ones.

Rongjie Lai, Jia Li

Low-rank structures play important role in recent advances of many problems in image science and data science. As a natural extension of low-rank structures for data with nonlinear structures, the concept of the low-dimensional manifold structure has been considered in many data processing problems. Inspired by this concept, we consider a manifold based low-rank regularization as a linear approximation of manifold dimension. This regularization is less restricted than the global low-rank regularization, and thus enjoy more flexibility to handle data with nonlinear structures. As applications, we demonstrate the proposed regularization to classical inverse problems in image sciences and data sciences including image inpainting, image super-resolution, X-ray computer tomography (CT) image reconstruction and semi-supervised learning. We conduct intensive numerical experiments in several image restoration problems and a semi-supervised learning problem of classifying handwritten digits using the MINST data. Our numerical tests demonstrate the effectiveness of the proposed methods and illustrate that the new regularization methods produce outstanding results by comparing with many existing methods.