Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image Generation

Text-to-image (T2I) generation has made significant advances in recent years, but challenges still remain in the generation of perceptual artifacts, misalignment with complex prompts, and safety. The prevailing approach to address these issues involves collecting human feedback on generated images, training reward models to estimate human feedback, and then fine-tuning T2I models based on the reward models to align them with human preferences. However, while existing reward fine-tuning methods can produce images with higher rewards, they may change model behavior in unexpected ways. For example, fine-tuning for one quality aspect (e.g., safety) may degrade other aspects (e.g., prompt alignment), or may lead to reward hacking (e.g., finding a way to increase rewards without having the intended effect). In this paper, we propose Focus-N-Fix, a region-aware fine-tuning method that trains models to correct only previously problematic image regions. The resulting fine-tuned model generates images with the same high-level structure as the original model but shows significant improvements in regions where the original model was deficient in safety (over-sexualization and violence), plausibility, or other criteria. Our experiments demonstrate that Focus-N-Fix improves these localized quality aspects with little or no degradation to others and typically imperceptible changes in the rest of the image. Disclaimer: This paper contains images that may be overly sexual, violent, offensive, or harmful.

HV-BEV: Decoupling Horizontal and Vertical Feature Sampling for Multi-View 3D Object Detection

The application of vision-based multi-view environmental perception system has been increasingly recognized in autonomous driving technology, especially the BEV-based models. Current state-of-the-art solutions primarily encode image features from each camera view into the BEV space through explicit or implicit depth prediction. However, these methods often focus on improving the accuracy of projecting 2D features into corresponding depth regions, while overlooking the highly structured information of real-world objects and the varying height distributions of objects across different scenes. In this work, we propose HV-BEV, a novel approach that decouples feature sampling in the BEV grid queries paradigm into horizontal feature aggregation and vertical adaptive height-aware reference point sampling, aiming to improve both the aggregation of objects' complete information and generalization to diverse road environments. Specifically, we construct a learnable graph structure in the horizontal plane aligned with the ground for 3D reference points, reinforcing the association of the same instance across different BEV grids, especially when the instance spans multiple image views around the vehicle. Additionally, instead of relying on uniform sampling within a fixed height range, we introduce a height-aware module that incorporates historical information, enabling the reference points to adaptively focus on the varying heights at which objects appear in different scenes. Extensive experiments validate the effectiveness of our proposed method, demonstrating its superior performance over the baseline across the nuScenes dataset. Moreover, our best-performing model achieves a remarkable 50.5% mAP and 59.8% NDS on the nuScenes testing set.

LVMark: Robust Watermark for latent video diffusion models

Rapid advancements in generative models have made it possible to create hyper-realistic videos. As their applicability increases, their unauthorized use has raised significant concerns, leading to the growing demand for techniques to protect the ownership of the generative model itself. While existing watermarking methods effectively embed watermarks into image-generative models, they fail to account for temporal information, resulting in poor performance when applied to video-generative models. To address this issue, we introduce a novel watermarking method called LVMark, which embeds watermarks into video diffusion models. A key component of LVMark is a selective weight modulation strategy that efficiently embeds watermark messages into the video diffusion model while preserving the quality of the generated videos. To accurately decode messages in the presence of malicious attacks, we design a watermark decoder that leverages spatio-temporal information in the 3D wavelet domain through a cross-attention module. To the best of our knowledge, our approach is the first to highlight the potential of video-generative model watermarking as a valuable tool for enhancing the effectiveness of ownership protection in video-generative models.

Motion Artifact Removal in Pixel-Frequency Domain via Alternate Masks and Diffusion Model

Motion artifacts present in magnetic resonance imaging (MRI) can seriously interfere with clinical diagnosis. Removing motion artifacts is a straightforward solution and has been extensively studied. However, paired data are still heavily relied on in recent works and the perturbations in \textit{k}-space (frequency domain) are not well considered, which limits their applications in the clinical field. To address these issues, we propose a novel unsupervised purification method which leverages pixel-frequency information of noisy MRI images to guide a pre-trained diffusion model to recover clean MRI images. Specifically, considering that motion artifacts are mainly concentrated in high-frequency components in \textit{k}-space, we utilize the low-frequency components as the guide to ensure correct tissue textures. Additionally, given that high-frequency and pixel information are helpful for recovering shape and detail textures, we design alternate complementary masks to simultaneously destroy the artifact structure and exploit useful information. Quantitative experiments are performed on datasets from different tissues and show that our method achieves superior performance on several metrics. Qualitative evaluations with radiologists also show that our method provides better clinical feedback. Our code is available at https://github.com/medcx/PFAD.

FastTrackTr:Towards Fast Multi-Object Tracking with Transformers

Transformer-based multi-object tracking (MOT) methods have captured the attention of many researchers in recent years. However, these models often suffer from slow inference speeds due to their structure or other issues. To address this problem, we revisited the Joint Detection and Tracking (JDT) method by looking back at past approaches. By integrating the original JDT approach with some advanced theories, this paper employs an efficient method of information transfer between frames on the DETR, constructing a fast and novel JDT-type MOT framework: FastTrackTr. Thanks to the superiority of this information transfer method, our approach not only reduces the number of queries required during tracking but also avoids the excessive introduction of network structures, ensuring model simplicity. Experimental results indicate that our method has the potential to achieve real-time tracking and exhibits competitive tracking accuracy across multiple datasets.

Multi-object Tracking by Detection and Query: an efficient end-to-end manner

Multi-object tracking is advancing through two dominant paradigms: traditional tracking by detection and newly emerging tracking by query. In this work, we fuse them together and propose the tracking-by-detection-and-query paradigm, which is achieved by a Learnable Associator. Specifically, the basic information interaction module and the content-position alignment module are proposed for thorough information Interaction among object queries. Tracking results are directly Decoded from these queries. Hence, we name the method as LAID. Compared to tracking-by-query models, LAID achieves competitive tracking accuracy with notably higher training efficiency. With regard to tracking-by-detection methods, experimental results on DanceTrack show that LAID significantly surpasses the state-of-the-art heuristic method by 3.9% on HOTA metric and 6.1% on IDF1 metric. On SportsMOT, LAID also achieves the best score on HOTA metric. By holding low training cost, strong tracking capabilities, and an elegant end-to-end approach all at once, LAID presents a forward-looking direction for the field.

Towards Student Actions in Classroom Scenes: New Dataset and Baseline

Analyzing student actions is an important and challenging task in educational research. Existing efforts have been hampered by the lack of accessible datasets to capture the nuanced action dynamics in classrooms. In this paper, we present a new multi-label student action video (SAV) dataset for complex classroom scenes. The dataset consists of 4,324 carefully trimmed video clips from 758 different classrooms, each labeled with 15 different actions displayed by students in classrooms. Compared to existing behavioral datasets, our dataset stands out by providing a wide range of real classroom scenarios, high-quality video data, and unique challenges, including subtle movement differences, dense object engagement, significant scale differences, varied shooting angles, and visual occlusion. The increased complexity of the dataset brings new opportunities and challenges for benchmarking action detection. Innovatively, we also propose a new baseline method, a visual transformer for enhancing attention to key local details in small and dense object regions. Our method achieves excellent performance with mean Average Precision (mAP) of 67.9\% and 27.4\% on SAV and AVA, respectively. This paper not only provides the dataset but also calls for further research into AI-driven educational tools that may transform teaching methodologies and learning outcomes. The code and dataset will be released at https://github.com/Ritatanz/SAV.

Cropper: Vision-Language Model for Image Cropping through In-Context Learning

The goal of image cropping is to identify visually appealing crops within an image. Conventional methods rely on specialized architectures trained on specific datasets, which struggle to be adapted to new requirements. Recent breakthroughs in large vision-language models (VLMs) have enabled visual in-context learning without explicit training. However, effective strategies for vision downstream tasks with VLMs remain largely unclear and underexplored. In this paper, we propose an effective approach to leverage VLMs for better image cropping. First, we propose an efficient prompt retrieval mechanism for image cropping to automate the selection of in-context examples. Second, we introduce an iterative refinement strategy to iteratively enhance the predicted crops. The proposed framework, named Cropper, is applicable to a wide range of cropping tasks, including free-form cropping, subject-aware cropping, and aspect ratio-aware cropping. Extensive experiments and a user study demonstrate that Cropper significantly outperforms state-of-the-art methods across several benchmarks.

ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling

Recognizing and disentangling visual attributes from objects is a foundation to many computer vision applications. While large vision language representations like CLIP had largely resolved the task of zero-shot object recognition, zero-shot visual attribute recognition remains a challenge because CLIP's contrastively-learned vision-language representation cannot effectively capture object-attribute dependencies. In this paper, we target this weakness and propose a sentence generation-based retrieval formulation for attribute recognition that is novel in 1) explicitly modeling a to-be-measured and retrieved object-attribute relation as a conditional probability graph, which converts the recognition problem into a dependency-sensitive language-modeling problem, and 2) applying a large pretrained Vision-Language Model (VLM) on this reformulation and naturally distilling its knowledge of image-object-attribute relations to use towards attribute recognition. Specifically, for each attribute to be recognized on an image, we measure the visual-conditioned probability of generating a short sentence encoding the attribute's relation to objects on the image. Unlike contrastive retrieval, which measures likelihood by globally aligning elements of the sentence to the image, generative retrieval is sensitive to the order and dependency of objects and attributes in the sentence. We demonstrate through experiments that generative retrieval consistently outperforms contrastive retrieval on two visual reasoning datasets, Visual Attribute in the Wild (VAW), and our newly-proposed Visual Genome Attribute Ranking (VGARank).

Fluid-Antenna Enhanced ISAC: Joint Antenna Positioning and Dual-Functional Beamforming Design under Perfect and Imperfect CSI

Integrated sensing and communication (ISAC) emerges as an essential technique for overcoming spectrum congestion. However, the performance of traditional ISAC systems with fixed-position-antennas (FPA) is limited due to insufficient spatial degree of freedom (DoF) exploration. Recently, fluid antenna (FA) with reconfigurable antenna position is developed to enhance the sensing and communication performance by reshaping the channel. This paper investigates an FA-enhanced ISAC system where a base station is equipped with multiple FAs to communicate with multiple single-antenna users and with FPAs to sense a point target. In this paper, we consider both perfect and imperfect channel state information (CSI) of the communication channel and sensing channel. In two cases, we focus on the maximization of the sensing signal-to-noise (SNR) by optimizing the positions of FAs and the dual-functional beamforming under the constraints of the FA moving region, the minimum FA distance and the minimum signal-to-interference-plus-noise (SINR) per user. Specifically, for the ideal case of perfect CSI, an iterative alternating optimization (AO) algorithm is proposed to tackle the formulated problem where the dual-functional beamforming and the FA positions are obtained via semidefinite relaxation (SDR) and successive convex approximation (SCA) techniques. Then, for the imperfect CSI case, we propose an AO-based iterative algorithm where $\mathcal{S}-$Procedure and SCA are applied to obtain the dual-functional beamforming and the FA positions. Furthermore, we analytically and numerically prove the convergence of the proposed algorithms. Numerical results demonstrate the notable gains of the proposed algorithms in the respective cases.