Author name cluster

Xu Jia

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.

6 papers

1 author row

AAAI Conference 2026 Conference Paper

Temporal Inconsistency Guidance for Super-resolution Video Quality Assessment

Yixiao Li
Xiaoyuan Yang
Weide Liu
Xin Jin
Xu Jia
Yu-Kun Lai
Paul L. Rosin
Hantao Liu

As super-resolution (SR) techniques introduce unique distortions that fundamentally differ from those caused by traditional degradation processes (e.g., compression), there is an increasing demand for specialized video quality assessment (VQA) methods tailored to SR-generated content. One critical factor affecting perceived quality is temporal inconsistency, which refers to irregularities between consecutive frames. However, existing VQA approaches rarely quantify this phenomenon or explicitly investigate its relationship with human perception. Moreover, SR videos exhibit amplified inconsistency levels as a result of enhancement processes. In this paper, we propose Temporal Inconsistency Guidance for Super-resolution Video Quality Assessment (TIG-SVQA) that underscores the critical role of temporal inconsistency in guiding the quality assessment of SR videos. We first design a perception-oriented approach to quantify frame-wise temporal inconsistency. Based on this, we introduce the Inconsistency Highlighted Spatial Module, which localizes inconsistent regions at both coarse and fine scales. Inspired by the human visual system, we further develop an Inconsistency Guided Temporal Module that performs progressive temporal feature aggregation: (1) a consistency-aware fusion stage in which a visual memory capacity block adaptively determines the information load of each temporal segment based on inconsistency levels, and (2) an informative filtering stage for emphasizing quality-related features. Extensive experiments on both single-frame and multi-frame SR video scenarios demonstrate that our method significantly outperforms state-of-the-art VQA approaches.

PDF Details DOI

EAAI Journal 2025 Journal Article

Knowledge-guided and Collaborative Learning Network for Camouflaged Object Detection

Dan Wu
Mengyin Wang
Jing Sun
Xu Jia

Camouflaged Object Detection (COD) task is more arduous than other target detection tasks because of the challenges of complex and variable contours, scale diversity, and high similarity to the background. Moreover, in pursuit of better detection performance, most existing COD methods usually require many parameters and computational complexity, which undoubtedly increases the difficulty and cost of implementation. In this paper, by revisiting this difficult task, we find that the collaborative effect of extracting explicit edge knowledge and global semantics highlights the camouflaged regions more and significantly affects detection efficiency. We propose a more comprehensible and efficient network for COD, namely the Knowledge-guided and Collaborative Learning Network (KCNet). It comes with more complex camouflaged targets by introducing rough features containing a large amount of edge knowledge and global semantics to interact with other components fully and collaborative learning. Specifically, we gradually introduce the rough features acquired by the preliminary perception unit to the layers by designing a knowledge-guided positioning module. Secondly, we design a detail enhancement module to enhance the extraction of the detailed parts of semantic information at deeper levels. Finally, we give a convolutional decoding unit to output the complete camouflaged target prediction information. Extensive experimental results show that our model reaches the state-of-the-art on four challenging datasets, outperforming 22 advanced models currently available. Meanwhile, KCNet exhibits a low number of parameters, a low computational complexity, and a very competitive inference speed, all of which are advantages over existing methods. The codes are released at https: //github. com/wd61419/KCNet.

Details DOI

AAAI Conference 2023 Conference Paper

Dual Memory Aggregation Network for Event-Based Object Detection with Learnable Representation

Dongsheng Wang
Xu Jia
Yang Zhang
Xinyu Zhang
Yaoyuan Wang
Ziyang Zhang
Dong Wang
Huchuan Lu

Event-based cameras are bio-inspired sensors that capture brightness change of every pixel in an asynchronous manner. Compared with frame-based sensors, event cameras have microsecond-level latency and high dynamic range, hence showing great potential for object detection under high-speed motion and poor illumination conditions. Due to sparsity and asynchronism nature with event streams, most of existing approaches resort to hand-crafted methods to convert event data into 2D grid representation. However, they are sub-optimal in aggregating information from event stream for object detection. In this work, we propose to learn an event representation optimized for event-based object detection. Specifically, event streams are divided into grids in the x-y-t coordinates for both positive and negative polarity, producing a set of pillars as 3D tensor representation. To fully exploit information with event streams to detect objects, a dual-memory aggregation network (DMANet) is proposed to leverage both long and short memory along event streams to aggregate effective information for object detection. Long memory is encoded in the hidden state of adaptive convLSTMs while short memory is modeled by computing spatial-temporal correlation between event pillars at neighboring time intervals. Extensive experiments on the recently released event-based automotive detection dataset demonstrate the effectiveness of the proposed method.

PDF Details DOI

AAAI Conference 2020 Conference Paper

Efficient Residual Dense Block Search for Image Super-Resolution

Dehua Song
Chang Xu
Xu Jia
Yiyi Chen
Chunjing Xu
Yunhe Wang

Although remarkable progress has been made on single image super-resolution due to the revival of deep convolutional neural networks, deep learning methods are confronted with the challenges of computation and memory consumption in practice, especially for mobile devices. Focusing on this issue, we propose an efﬁcient residual dense block search algorithm with multiple objectives to hunt for fast, lightweight and accurate networks for image super-resolution. Firstly, to accelerate super-resolution network, we exploit the variation of feature scale adequately with the proposed efﬁcient residual dense blocks. In the proposed evolutionary algorithm, the locations of pooling and upsampling operator are searched automatically. Secondly, network architecture is evolved with the guidance of block credits to acquire accurate superresolution network. The block credit reﬂects the effect of current block and is earned during model evaluation process. It guides the evolution by weighing the sampling probability of mutation to favor admirable blocks. Extensive experimental results demonstrate the effectiveness of the proposed searching method and the found efﬁcient super-resolution models achieve better performance than the state-of-the-art methods with limited number of parameters and FLOPs.

PDF Details

NeurIPS Conference 2017 Conference Paper

Pose Guided Person Image Generation

Liqian Ma
Xu Jia
Qianru Sun
Bernt Schiele
Tinne Tuytelaars
Luc Van Gool

This paper proposes the novel Pose Guided Person Generation Network (PG$^2$) that allows to synthesize person images in arbitrary poses, based on an image of that person and a novel pose. Our generation framework PG$^2$ utilizes the pose information explicitly and consists of two key stages: pose integration and image refinement. In the first stage the condition image and the target pose are fed into a U-Net-like network to generate an initial but coarse image of the person with the target pose. The second stage then refines the initial and blurry result by training a U-Net-like generator in an adversarial way. Extensive experimental results on both 128$\times$64 re-identification images and 256$\times$256 fashion photos show that our model generates high-quality person images with convincing details.

PDF Details

NeurIPS Conference 2016 Conference Paper

Dynamic Filter Networks

Xu Jia
Bert De Brabandere
Tinne Tuytelaars
Luc Gool

In a traditional convolutional layer, the learned filters stay fixed after training. In contrast, we introduce a new framework, the Dynamic Filter Network, where filters are generated dynamically conditioned on an input. We show that this architecture is a powerful one, with increased flexibility thanks to its adaptive nature, yet without an excessive increase in the number of model parameters. A wide variety of filtering operation can be learned this way, including local spatial transformations, but also others like selective (de)blurring or adaptive feature extraction. Moreover, multiple such layers can be combined, e. g. in a recurrent architecture. We demonstrate the effectiveness of the dynamic filter network on the tasks of video and stereo prediction, and reach state-of-the-art performance on the moving MNIST dataset with a much smaller model. By visualizing the learned filters, we illustrate that the network has picked up flow information by only looking at unlabelled training data. This suggests that the network can be used to pretrain networks for various supervised tasks in an unsupervised way, like optical flow and depth estimation.

PDF Details