Xu Yang

He Wang, Yang Xu, Zebin Wu et al.

Hyperspectral and multispectral image fusion aims to generate high spectral and spatial resolution hyperspectral images (HR-HSI) by fusing high-resolution multispectral images (HR-MSI) and low-resolution hyperspectral images (LR-HSI). However, existing fusion methods encounter challenges such as unknown degradation parameters, incomplete exploitation of the correlation between high-dimensional structures and deep image features. To overcome these issues, in this article, an unsupervised blind fusion method for hyperspectral and multispectral images based on Tucker decomposition and spatial spectral manifold learning (DTDNML) is proposed. We design a novel deep Tucker decomposition network that maps LR-HSI and HR-MSI into a consistent feature space, achieving reconstruction through decoders with shared parameter. To better exploit and fuse spatial-spectral features in the data, we design a core tensor fusion network that incorporates a spatial spectral attention mechanism for aligning and fusing features at different scales. Furthermore, to enhance the capacity in capturing global information, a Laplacian-based spatial-spectral manifold constraints is introduced in shared-decoders. Sufficient experiments have validated that this method enhances the accuracy and efficiency of hyperspectral and multispectral fusion on different remote sensing datasets. The source code is available at https://github.com/Shawn-H-Wang/DTDNML.

Yaya Shi, Xu Yang, Haiyang Xu et al.

Current metrics for video captioning are mostly based on the text-level comparison between reference and candidate captions. However, they have some insuperable drawbacks, e.g., they cannot handle videos without references, and they may result in biased evaluation due to the one-to-many nature of video-to-text and the neglect of visual relevance. From the human evaluator's viewpoint, a high-quality caption should be consistent with the provided video, but not necessarily be similar to the reference in literal or semantics. Inspired by human evaluation, we propose EMScore (Embedding Matching-based score), a novel reference-free metric for video captioning, which directly measures similarity between video and candidate captions. Benefit from the recent development of large-scale pre-training models, we exploit a well pre-trained vision-language model to extract visual and linguistic embeddings for computing EMScore. Specifically, EMScore combines matching scores of both coarse-grained (video and caption) and fine-grained (frames and words) levels, which takes the overall understanding and detailed characteristics of the video into account. Furthermore, considering the potential information gain, EMScore can be flexibly extended to the conditions where human-labeled references are available. Last but not least, we collect VATEX-EVAL and ActivityNet-FOIl datasets to systematically evaluate the existing metrics. VATEX-EVAL experiments demonstrate that EMScore has higher human correlation and lower reference dependency. ActivityNet-FOIL experiment verifies that EMScore can effectively identify "hallucinating" captions. The datasets will be released to facilitate the development of video captioning metrics. The code is available at: https://github.com/ShiYaya/emscore.

Lu Zhang, Xiangyu Zhu, Xiangyu Chen et al.

Multispectral pedestrian detection has shown great advantages under poor illumination conditions, since the thermal modality provides complementary information for the color image. However, real multispectral data suffers from the position shift problem, i.e. the color-thermal image pairs are not strictly aligned, making one object has different positions in different modalities. In deep learning based methods, this problem makes it difficult to fuse the feature maps from both modalities and puzzles the CNN training. In this paper, we propose a novel Aligned Region CNN (AR-CNN) to handle the weakly aligned multispectral data in an end-to-end way. Firstly, we design a Region Feature Alignment (RFA) module to capture the position shift and adaptively align the region features of the two modalities. Secondly, we present a new multimodal fusion method, which performs feature re-weighting to select more reliable features and suppress the useless ones. Besides, we propose a novel RoI jitter strategy to improve the robustness to unexpected shift patterns of different devices and system settings. Finally, since our method depends on a new kind of labelling: bounding boxes that match each modality, we manually relabel the KAIST dataset by locating bounding boxes in both modalities and building their relationships, providing a new KAIST-Paired Annotation. Extensive experimental validations on existing datasets are performed, demonstrating the effectiveness and robustness of the proposed method. Code and data are available at https://github.com/luzhang16/AR-CNN.

Ruizhe Zeng, Lu Zhang, Xu Yang et al.

Open-vocabulary object detection is the task of accurately detecting objects from a candidate vocabulary list that includes both base and novel categories. Currently, numerous open-vocabulary detectors have achieved success by leveraging the impressive zero-shot capabilities of CLIP. However, we observe that CLIP models struggle to effectively handle background images (i.e. images without corresponding labels) due to their language-image learning methodology. This limitation results in suboptimal performance for open-vocabulary detectors that rely on CLIP when processing background samples. In this paper, we propose Background Information Representation for open-vocabulary Detector (BIRDet), a novel approach to address the limitations of CLIP in handling background samples. Specifically, we design Background Information Modeling (BIM) to replace the single, fixed background embedding in mainstream open-vocabulary detectors with dynamic scene information, and prompt it into image-related background representations. This method effectively enhances the ability to classify oversized regions as background. Besides, we introduce Partial Object Suppression (POS), an algorithm that utilizes the ratio of overlap area to address the issue of misclassifying partial regions as foreground. Experiments on OV-COCO and OV-LVIS benchmarks demonstrate that our proposed model is capable of achieving performance enhancements across various open-vocabulary detectors.

Xu Yang

Face photo sketch synthesis has got some researchers' attention in recent years because of its potential applications in digital entertainment and law enforcement. Some patches based methods have been proposed to solve this problem. These methods usually focus more on how to get a sketch patch for a given photo patch than how to blend these generated patches. However, without appropriately blending method, some jagged parts and mottled points will appear in the entire face sketch. In order to get a smoother sketch, we propose a new method to reduce such jagged parts and mottled points. In our system, we resort to an existed method, which is Markov Random Fields (MRF), to train a crude face sketch firstly. Then this crude sketch face sketch will be divided into some larger patches again and retrained by Non-Negative Matrix Factorization (NMF). At last, we use Multiresolution Spline and a blend trick named full-coverage trick to blend these retrained patches. The experiment results show that compared with some previous method, we can get a smoother face sketch.