Hengcan Shi

Large-scale images play a crucial role in geospatial surveying, as they cover an extensively broad view and diverse objects. Due to computational limitations, existing methods rely on generating large-scale images in patches. However, the lack of global guidance in these methods often leads to significant logical errors among different patches. To address this issue, we propose a Global Consistency Diffusion model (Glob-Diffusion) for large-scale image generation. The core idea is to utilize the global consistency of small-scale images to guide the generation of large-scale images. Specifically, we introduce a Hierarchical Distributed Guidance (HDG) module that extracts patch prompts with different semantic hierarchies from small-scale images, distributedly embedding them into the generation of large-scale images to maintain global consistency across various regions. In addition, we further design a Region Guided Adapter (RGA) that dynamically optimizes the guidance strength of patch prompts by comparing differences across generated regions, effectively improving the realism of large-scale images. Our method demonstrates remarkable visual synthesis results across various natural scenes, effectively preserving global consistency in large-scale images, and also significantly enhancing the generation quality of large-scale remote sensing images. Code will be available at https://github.com/kyh433/Glob-Diffusion.

Micro-expression recognition (MER) has drawn increasing attention in recent years due to its ability to reveal the true feelings people want to hide. The key challenge in MER is subtle motions, which are hard to capture but crucial for MER. Existing methods usually solve this problem by magnifying all motions in the whole face and temporal sequence. However, micro-expressions (MEs) only involve a few facial areas and several temporal snippets. The all-motion magnification in previous methods cannot precisely capture these local ME motion patterns, and can easily cause spatial as well as temporal distortions, which significantly decrease the MER accuracy. In this paper, we propose an RGB-Frequency Relation Exploration Network (RF-REN), which enhances the subtle motions in refined local ME cues by exploring spatial and temporal relations in both RGB and frequency domains. Specifically, we first decompose the ME video into RGB as well as frequency domains, and conduct temporal division according to different motion stages to cover various ME local patterns. Secondly, we construct an adaptive local-global relation exploration (LGRE) module to explore the local relation cues in the spatial appearance and temporal dynamics in both domains. Finally, we propose an RGB-Frequency routing strategy to fuse the RGB and frequency cues, aiming to aggregate spatial-temporal local-global information and enhance subtle motions for MER. Extensive experiments on three databases (CASME II, SAMM and SMIC) show that the proposed model outperforms other state-of-the-art methods.

In recent years, open-vocabulary (OV) dense visual prediction (such as OV object detection, semantic, instance and panoptic segmentations) has attracted increasing research attention. However, most of the existing approaches are task-specific, i.e., tackling each task individually. In this paper, we propose a Unified Open-Vocabulary Network (UOVN) to jointly address four common dense prediction tasks. Compared with separate models, a unified network is more desirable for diverse industrial applications. Moreover, OV dense prediction training data is relatively less. Separate networks can only leverage task-relevant training data, while a unified approach can integrate diverse data to boost individual tasks. We address two major challenges in unified OV prediction. Firstly, unlike unified methods for fixed-set predictions, OV networks are usually trained with multi-modal data. Therefore, we propose a multi-modal, multi-scale and multi-task (MMM) decoding mechanism to better exploit multi-modal information for OV recognition. Secondly, because UOVN uses data from different tasks for training, there are significant domain and task gaps. We present a UOVN training mechanism to reduce such gaps. Experiments on four datasets demonstrate the effectiveness of our UOVN.

Scene text recognition is an important and challenging task in computer vision. However, most prior works focus on recognizing pre-defined words, while there are various out-of-vocabulary (OOV) words in real-world applications. In this paper, we propose a novel open-vocabulary text recognition framework, Pseudo-OCR, to recognize OOV words. The key challenge in this task is the lack of OOV training data. To solve this problem, we first propose a pseudo label generation module that leverages character detection and image inpainting to produce substantial pseudo OOV training data from real-world images. Unlike previous synthetic data, our pseudo OOV data contains real characters and backgrounds to simulate real-world applications. Secondly, to reduce noises in pseudo data, we present a semantic checking mechanism to filter semantically meaningful data. Thirdly, we introduce a quality-aware margin loss to boost the training with pseudo data. Our loss includes a margin-based part to enhance the classification ability, and a quality-aware part to penalize low-quality samples in both real and pseudo data. Extensive experiments demonstrate that our approach outperforms the state-of-the-art on eight datasets and achieves the first rank in the ICDAR2022 challenge.