Panoptic Scene Graph Generation (PSG) translates visual scenes to structured linguistic descriptions, i.e., mapping visual instances to subjects/objects, and their relationships to predicates. However, the annotators' preferences and semantic overlaps between predicates inevitably lead to the semantic mappings of multiple predicates to one relationship, i.e., biased-predicate annotations. As a result, with the contradictory mapping between visual and linguistics, PSG models are struggled to construct clear decision planes among predicates, so as to cause existing poor performances. Obviously, it is essential for the PSG task to tackle this multi-modal contradiction. Therefore, we propose a novel method that utilizes unbiased visual predicate representations for Biased-Annotation Identification (BAI) as a fundamental step for PSG/SGG tasks. Our BAI includes three main steps: predicate representation extraction, predicate representation debiasing, and biased-annotation identification. With flexible biased annotation processing methods, our BAI can act as a fundamental step of dataset debiasing. Experimental results demonstrate that our proposed BAI has achieved state-of-the-art performance, which promotes the performance of benchmark models to various degrees with ingenious biased annotation processing methods. Furthermore, our BAI shows great generalization and effectiveness on multiple datasets. Our codes are released at https://github.com/lili0415/BAI.

In the realm of video dialog response generation, capturing both the essence of video content and the temporal nuances of conversation history is crucial. While some approaches rely on large-scale pretrained visual-language models, often neglecting temporal dynamics, others emphasize spatial-temporal relationships within videos but demand intricate object trajectory pre-extractions and overlook dialog temporal dynamics. This paper introduces the Dual Temporal Grounding-enhanced Video Dialog model (DTGVD), designed to bridge the gap between these two approaches. DTGVD uniquely integrates the strengths of both by emphasizing dual temporal relationships. It achieves this by predicting dialog turn-specific temporal regions, selectively filtering video content, and grounding responses in both video and dialog contexts.A key innovation of DTGVD is its advanced handling of chronological interplay within dialogs. By effectively capturing and leveraging dependencies between dialog turns, it enables a more nuanced understanding of conversational dynamics. To further align video and dialog temporal dynamics, we introduce a list-wise contrastive learning strategy. In this framework, accurately grounded turn-clip pairings are treated as positive samples, while less precise pairings serve as negative samples. This refined classification is then seamlessly integrated into our end-to-end response generation mechanism.Evaluations using AVSD@DSTC-7 and AVSD@DSTC-8 datasets underscore the superiority of our methodology.

Satellite-to-radar translation is a critical yet under-explored task in modern weather forecasting. While satellites provide near-global coverage and high-frequency updates, their multi-channel radiance data is difficult to interpret directly by forecasters or end-users, and not readily compatible with existing radar-based forecasting models. By converting satellite observations into radar-equivalent representations, we can (i) extend radar-like availability to regions without ground-based radar coverage, (ii) provide a more compact and operationally meaningful representation of storms, and (iii) enable the reuse of a large ecosystem of radar-based nowcasting models without retraining. Despite its importance, methods tailored for this task remain limited, and the performance of general-purpose generative models has not been systematically benchmarked. To fill this gap, we propose SRDiff, a cross-modal, sequence-aware diffusion model specifically designed for satellite-to-radar translation. SRDiff employs a Cross-Modal Conditional Adapter to align heterogeneous satellite channels with radar reflectivity, and a Diffusion Transformer backbone to capture sequential dependencies, producing stable and coherent radar predictions. Extensive experiments on the SEVIR and Sat2Rdr datasets show that SRDiff outperforms existing deterministic and diffusion-based methods on the satellite-to-radar translation task across all key metrics. As a downstream application, we integrate SRDiff with off-the-shelf radar-based nowcasting models, demonstrating three key advantages: (i) operational efficiency, since no new training is required, (ii) strong forecasting accuracy, often surpassing models trained from scratch, and (iii) practical validation that effective satellite-to-radar translation directly improves downstream now-casting. Code is available at https://github.com/42xingxing/SRDiff.

Pansharpening is a fundamental task in remote sensing that aims to fuse high-spatial-resolution panchromatic images with low-spatial-resolution multispectral images. Inspired by the remarkable success of diffusion models in generative tasks, recent studies have introduced them to this field, yielding promising results. However, existing diffusion-based methods remain constrained by computationally expensive multi-step sampling processes or a heavy reliance on complex prior knowledge. To overcome these limitations, we propose InstaFlow-Pan, a novel flow-matching-based model capable of generating high-fidelity high-resolution multispectral images in a single inference step. Specifically, we employ a residual learning strategy and predict clean residuals instead of complex velocity fields directly. This reduces the information load, enabling the model to bypass iterative integration and achieve high-fidelity one-step synthesis. To support this paradigm, we design a conditional feature encoder based on the pyramid vision Transformer to extract robust conditional feature representations. We then build a generative network architecture leveraging multi-scale and attention mechanisms, which simultaneously preserves local details and global semantic information while enabling flexible guidance from conditional features. Furthermore, we introduce a novel progressive frequency-aware training strategy, which dynamically modulates the supervision focus along the flow trajectory, prioritizing global structure recovery in near-noise regions while progressively reinforcing high-frequency detail constraints as the generative process advances. Extensive experiments on multiple benchmark datasets demonstrate that InstaFlow-Pan outperforms state-of-the-art diffusion-based and regression-based methods, achieving superior spectral fidelity and spatial detail preservation.

Temporal Sentence Grounding in Videos (TSGV) aims to localize video moments that are semantically consistent with a given query. Despite the proliferation of approaches to TSGV in recent years, existing methods still face limitations in localizing micro-moments in videos and struggle to capture meaningful fine-grained event information within them. To address these challenges, we propose a Dynamic Graph-enhanced Event Refinement (DGER) framework specifically designed for the Temporal Sentence Grounding of Micro-moments (Micro-TSG) task. This framework efficiently explores event-aware information among text queries, long videos, and micro-moments. Our approach begins with a Query-specific Event-aware module that includes a modality-specific encoding module, a multi-modal fusion module, and an event- and query-refinement processing module. These components comprehensively leverage fine-grained event information both within and across modal contexts. Additionally, we have designed a Dynamic Information Propagation module that automatically refines the structure of attentional regions based on the Graph Information Bottleneck (GIB) principle, enhancing the attentional mechanism's ability to efficiently extract key features from significantly short-depth signals. Extensive experiments demonstrate that the proposed method outperforms all state-of-the-art techniques on the Charades-STA and TACoS datasets, achieving comparable results on the ActivityNet Captions dataset.