Unwarping Screen Content Images via Structure-texture Enhancement Network and Transformation Self-estimation

While existing implicit neural network-based image unwarping methods perform well on natural images, they struggle to handle screen content images (SCIs), which often contain large geometric distortions, text, symbols, and sharp edges. To address this, we propose a structure-texture enhancement network (STEN) with transformation self-estimation for SCI warping. STEN integrates a B-spline implicit neural representation module and a transformation error estimation and self-correction algorithm. It comprises two branches: the structure estimation branch (SEB), which enhances local aggregation and global dependency modeling, and the texture estimation branch (TEB), which improves texture detail synthesis using B-spline implicit neural representation. Additionally, the transformation self-estimation module autonomously estimates the transformation error and corrects the coordinate transformation matrix, effectively handling real-world image distortions. Extensive experiments on public SCI datasets demonstrate that our approach significantly outperforms state-of-the-art methods. Comparisons on well-known natural image datasets also show the potential of our approach for natural image distortion.

Few-Shot Referring Video Single- and Multi-Object Segmentation via Cross-Modal Affinity with Instance Sequence Matching

Referring video object segmentation (RVOS) aims to segment objects in videos guided by natural language descriptions. We propose FS-RVOS, a Transformer-based model with two key components: a cross-modal affinity module and an instance sequence matching strategy, which extends FS-RVOS to multi-object segmentation (FS-RVMOS). Experiments show FS-RVOS and FS-RVMOS outperform state-of-the-art methods across diverse benchmarks, demonstrating superior robustness and accuracy.

GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding

Pixel grounding, encompassing tasks such as Referring Expression Segmentation (RES), has garnered considerable attention due to its immense potential for bridging the gap between vision and language modalities. However, advancements in this domain are currently constrained by limitations inherent in existing datasets, including limited object categories, insufficient textual diversity, and a scarcity of high-quality annotations. To mitigate these limitations, we introduce GroundingSuite, which comprises: (1) an automated data annotation framework leveraging multiple Vision-Language Model (VLM) agents; (2) a large-scale training dataset encompassing 9.56 million diverse referring expressions and their corresponding segmentations; and (3) a meticulously curated evaluation benchmark consisting of 3,800 images. The GroundingSuite training dataset facilitates substantial performance improvements, enabling models trained on it to achieve state-of-the-art results. Specifically, a cIoU of 68.9 on gRefCOCO and a gIoU of 55.3 on RefCOCOm. Moreover, the GroundingSuite annotation framework demonstrates superior efficiency compared to the current leading data annotation method, i.e., $4.5 \times$ faster than the GLaMM.

CLIP-SR: Collaborative Linguistic and Image Processing for Super-Resolution

Convolutional Neural Networks (CNNs) have advanced Image Super-Resolution (SR), but most CNN-based methods rely solely on pixel-based transformations, often leading to artifacts and blurring, particularly with severe downsampling (e.g., 8x or 16x). Recent text-guided SR methods attempt to leverage textual information for enhanced detail, but they frequently struggle with effective alignment, resulting in inconsistent semantic coherence. To address these limitations, we introduce a multi-modal semantic enhancement approach that combines textual semantics with visual features, effectively tackling semantic mismatches and detail loss in highly degraded LR images. Our proposed multi-modal collaborative framework enables the production of realistic and high-quality SR images at significant up-scaling factors. The framework integrates text and image inputs, employing a prompt predictor, Text-Image Fusion Block (TIFBlock), and Iterative Refinement Module alongside CLIP (Contrastive Language-Image Pretraining) features to guide a progressive enhancement process with fine-grained alignment. This alignment produces high-resolution outputs with crisp details and semantic coherence, even at large scaling factors. Through extensive comparative experiments and ablation studies, we validate the effectiveness of our approach. Additionally, by incorporating textual semantic guidance, our technique enables a degree of super-resolution editability while maintaining semantic coherence.

Marco-LLM: Bridging Languages via Massive Multilingual Training for Cross-Lingual Enhancement

Large Language Models (LLMs) have achieved remarkable progress in recent years; however, their excellent performance is still largely limited to major world languages, primarily English. Many LLMs continue to face challenges with multilingual tasks, especially when it comes to low-resource languages. To address this issue, we introduced Marco-LLM: Massive multilingual training for cross-lingual enhancement LLM. We have collected a substantial amount of multilingual data for several low-resource languages and conducted extensive continual pre-training using the Qwen2 models. This effort has resulted in a multilingual LLM named Marco-LLM. Through comprehensive evaluations on various multilingual benchmarks, including MMMLU, AGIEval, Belebele, Flores-200, XCOPA and many others, Marco-LLM has demonstrated substantial improvements over state-of-the-art LLMs. Furthermore, Marco-LLM achieved substantial enhancements in any-to-any machine translation tasks, showing the effectiveness of our multilingual LLM. Marco-LLM is a pioneering multilingual LLM designed to not only perform exceptionally well in multilingual tasks, including low-resource languages, but also maintain strong performance in English and other major languages, closing the performance gap between high- and low-resource language capabilities. By bridging languages, this effort demonstrates our dedication to ensuring LLMs work accurately across various languages.

Frequency Diverse Array-enabled RIS-aided Integrated Sensing and Communication

Integrated sensing and communication (ISAC) has been envisioned as a prospective technology to enable ubiquitous sensing and communications in next-generation wireless networks. In contrast to existing works on reconfigurable intelligent surface (RIS) aided ISAC systems using conventional phased arrays (PAs), this paper investigates a frequency diverse array (FDA)-enabled RIS-aided ISAC system, where the FDA aims to provide a distance-angle-dependent beampattern to effectively suppress the clutter, and RIS is employed to establish high-quality links between the BS and users/target. We aim to maximize sum rate by jointly optimizing the BS transmit beamforming vectors, the covariance matrix of the dedicated radar signal, the RIS phase shift matrix, the FDA frequency offsets and the radar receive equalizer, while guaranteeing the required signal-to-clutter-plus-noise ratio (SCNR) of the radar echo signal. To tackle this challenging problem, we first theoretically prove that the dedicated radar signal is unnecessary for enhancing target sensing performance, based on which the original problem is much simplified. Then, we turn our attention to the single-user single-target (SUST) scenario to demonstrate that the FDA-RIS-aided ISAC system always achieves a higher SCNR than its PA-RIS-aided counterpart. Moreover, it is revealed that the SCNR increment exhibits linear growth with the BS transmit power and the number of BS receive antennas. In order to effectively solve this simplified problem, we leverage the fractional programming (FP) theory and subsequently develop an efficient alternating optimization (AO) algorithm based on symmetric alternating direction method of multipliers (SADMM) and successive convex approximation (SCA) techniques. Numerical results demonstrate the superior performance of our proposed algorithm in terms of sum rate and radar SCNR.

Massive MIMO-OTFS-Based Random Access for Cooperative LEO Satellite Constellations

This paper investigates joint device identification, channel estimation, and symbol detection for cooperative multi-satellite-enhanced random access, where orthogonal time-frequency space modulation with the large antenna array is utilized to combat the dynamics of the terrestrial-satellite links (TSLs). We introduce the generalized complex exponential basis expansion model to parameterize TSLs, thereby reducing the pilot overhead. By exploiting the block sparsity of the TSLs in the angular domain, a message passing algorithm is designed for initial channel estimation. Subsequently, we examine two cooperative modes to leverage the spatial diversity within satellite constellations: the centralized mode, where computations are performed at a high-power central server, and the distributed mode, where computations are offloaded to edge satellites with minimal signaling overhead. Specifically, in the centralized mode, device identification is achieved by aggregating backhaul information from edge satellites, and channel estimation and symbol detection are jointly enhanced through a structured approximate expectation propagation (AEP) algorithm. In the distributed mode, edge satellites share channel information and exchange soft information about data symbols, leading to a distributed version of AEP. The introduced basis expansion model for TSLs enables the efficient implementation of both centralized and distributed algorithms via fast Fourier transform. Simulation results demonstrate that proposed schemes significantly outperform conventional algorithms in terms of the activity error rate, the normalized mean squared error, and the symbol error rate. Notably, the distributed mode achieves performance comparable to the centralized mode with only two exchanges of soft information about data symbols within the constellation.

EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model

Segment Anything Model (SAM) has attracted widespread attention for its superior interactive segmentation capabilities with visual prompts while lacking further exploration of text prompts. In this paper, we empirically investigate what text prompt encoders (e.g., CLIP or LLM) are good for adapting SAM for referring expression segmentation and introduce the Early Vision-language Fusion-based SAM (EVF-SAM). EVF-SAM is a simple yet effective referring segmentation method which exploits multimodal prompts (i.e., image and text) and comprises a pre-trained vision-language model to generate referring prompts and a SAM model for segmentation. Surprisingly, we observe that: (1) multimodal prompts and (2) vision-language models with early fusion (e.g., BEIT-3) are beneficial for prompting SAM for accurate referring segmentation. Our experiments show that the proposed EVF-SAM based on BEIT-3 can obtain state-of-the-art performance on RefCOCO/+/g for referring expression segmentation and demonstrate the superiority of prompting SAM with early vision-language fusion. In addition, the proposed EVF-SAM with 1.32B parameters achieves remarkably higher performance while reducing nearly 82% of parameters compared to previous SAM methods based on large multimodal models.

AI Generated Signal for Wireless Sensing

Deep learning has significantly advanced wireless sensing technology by leveraging substantial amounts of high-quality training data. However, collecting wireless sensing data encounters diverse challenges, including unavoidable data noise, limited data scale due to significant collection overhead, and the necessity to reacquire data in new environments. Taking inspiration from the achievements of AI-generated content, this paper introduces a signal generation method that achieves data denoising, augmentation, and synthesis by disentangling distinct attributes within the signal, such as individual and environment. The approach encompasses two pivotal modules: structured signal selection and signal disentanglement generation. Structured signal selection establishes a minimal signal set with the target attributes for subsequent attribute disentanglement. Signal disentanglement generation disentangles the target attributes and reassembles them to generate novel signals. Extensive experimental results demonstrate that the proposed method can generate data that closely resembles real-world data on two wireless sensing datasets, exhibiting state-of-the-art performance. Our approach presents a robust framework for comprehending and manipulating attribute-specific information in wireless sensing.

Learning Cross-Modal Affinity for Referring Video Object Segmentation Targeting Limited Samples

Referring video object segmentation (RVOS), as a supervised learning task, relies on sufficient annotated data for a given scene. However, in more realistic scenarios, only minimal annotations are available for a new scene, which poses significant challenges to existing RVOS methods. With this in mind, we propose a simple yet effective model with a newly designed cross-modal affinity (CMA) module based on a Transformer architecture. The CMA module builds multimodal affinity with a few samples, thus quickly learning new semantic information, and enabling the model to adapt to different scenarios. Since the proposed method targets limited samples for new scenes, we generalize the problem as - few-shot referring video object segmentation (FS-RVOS). To foster research in this direction, we build up a new FS-RVOS benchmark based on currently available datasets. The benchmark covers a wide range and includes multiple situations, which can maximally simulate real-world scenarios. Extensive experiments show that our model adapts well to different scenarios with only a few samples, reaching state-of-the-art performance on the benchmark. On Mini-Ref-YouTube-VOS, our model achieves an average performance of 53.1 J and 54.8 F, which are 10% better than the baselines. Furthermore, we show impressive results of 77.7 J and 74.8 F on Mini-Ref-SAIL-VOS, which are significantly better than the baselines. Code is publicly available at https://github.com/hengliusky/Few_shot_RVOS.