Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints

Multi-task visual grounding involves the simultaneous execution of localization and segmentation in images based on textual expressions. The majority of advanced methods predominantly focus on transformer-based multimodal fusion, aiming to extract robust multimodal representations. However, ambiguity between referring expression comprehension (REC) and referring image segmentation (RIS) is error-prone, leading to inconsistencies between multi-task predictions. Besides, insufficient multimodal understanding directly contributes to biased target perception. To overcome these challenges, we propose a Coarse-to-fine Consistency Constraints Visual Grounding architecture ($\text{C}^3\text{VG}$), which integrates implicit and explicit modeling approaches within a two-stage framework. Initially, query and pixel decoders are employed to generate preliminary detection and segmentation outputs, a process referred to as the Rough Semantic Perception (RSP) stage. These coarse predictions are subsequently refined through the proposed Mask-guided Interaction Module (MIM) and a novel explicit bidirectional consistency constraint loss to ensure consistent representations across tasks, which we term the Refined Consistency Interaction (RCI) stage. Furthermore, to address the challenge of insufficient multimodal understanding, we leverage pre-trained models based on visual-linguistic fusion representations. Empirical evaluations on the RefCOCO, RefCOCO+, and RefCOCOg datasets demonstrate the efficacy and soundness of $\text{C}^3\text{VG}$, which significantly outperforms state-of-the-art REC and RIS methods by a substantial margin. Code and model will be available at \url{https://github.com/Dmmm1997/C3VG}.

ST$^3$: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming

Multimodal large language models (MLLMs) enhance their perceptual capabilities by integrating visual and textual information. However, processing the massive number of visual tokens incurs a significant computational cost. Existing analysis of the MLLM attention mechanisms remains shallow, leading to coarse-grain token pruning strategies that fail to effectively balance speed and accuracy. In this paper, we conduct a comprehensive investigation of MLLM attention mechanisms with LLaVA. We find that numerous visual tokens and partial attention computations are redundant during the decoding process. Based on this insight, we propose Spatial-Temporal Visual Token Trimming ($\textbf{ST}^{3}$), a framework designed to accelerate MLLM inference without retraining. $\textbf{ST}^{3}$ consists of two primary components: 1) Progressive Visual Token Pruning (\textbf{PVTP}), which eliminates inattentive visual tokens across layers, and 2) Visual Token Annealing (\textbf{VTA}), which dynamically reduces the number of visual tokens in each layer as the generated tokens grow. Together, these techniques deliver around $\mathbf{2\times}$ faster inference with only about $\mathbf{30\%}$ KV cache memory compared to the original LLaVA, while maintaining consistent performance across various datasets. Crucially, $\textbf{ST}^{3}$ can be seamlessly integrated into existing pre-trained MLLMs, providing a plug-and-play solution for efficient inference.

Enhancing Facial Consistency in Conditional Video Generation via Facial Landmark Transformation

Landmark-guided character animation generation is an important field. Generating character animations with facial features consistent with a reference image remains a significant challenge in conditional video generation, especially involving complex motions like dancing. Existing methods often fail to maintain facial feature consistency due to mismatches between the facial landmarks extracted from source videos and the target facial features in the reference image. To address this problem, we propose a facial landmark transformation method based on the 3D Morphable Model (3DMM). We obtain transformed landmarks that align with the target facial features by reconstructing 3D faces from the source landmarks and adjusting the 3DMM parameters to match the reference image. Our method improves the facial consistency between the generated videos and the reference images, effectively improving the facial feature mismatch problem.

FashionR2R: Texture-preserving Rendered-to-Real Image Translation with Diffusion Models

Modeling and producing lifelike clothed human images has attracted researchers' attention from different areas for decades, with the complexity from highly articulated and structured content. Rendering algorithms decompose and simulate the imaging process of a camera, while are limited by the accuracy of modeled variables and the efficiency of computation. Generative models can produce impressively vivid human images, however still lacking in controllability and editability. This paper studies photorealism enhancement of rendered images, leveraging generative power from diffusion models on the controlled basis of rendering. We introduce a novel framework to translate rendered images into their realistic counterparts, which consists of two stages: Domain Knowledge Injection (DKI) and Realistic Image Generation (RIG). In DKI, we adopt positive (real) domain finetuning and negative (rendered) domain embedding to inject knowledge into a pretrained Text-to-image (T2I) diffusion model. In RIG, we generate the realistic image corresponding to the input rendered image, with a Texture-preserving Attention Control (TAC) to preserve fine-grained clothing textures, exploiting the decoupled features encoded in the UNet structure. Additionally, we introduce SynFashion dataset, featuring high-quality digital clothing images with diverse textures. Extensive experimental results demonstrate the superiority and effectiveness of our method in rendered-to-real image translation.

FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance

CLIP has achieved impressive zero-shot performance after pre-training on a large-scale dataset consisting of paired image-text data. Previous works have utilized CLIP by incorporating manually designed visual prompts like colored circles and blur masks into the images to guide the model's attention, showing enhanced zero-shot performance in downstream tasks. Although these methods have achieved promising results, they inevitably alter the original information of the images, which can lead to failure in specific tasks. We propose a train-free method Foveal-Attention CLIP (FALIP), which adjusts the CLIP's attention by inserting foveal attention masks into the multi-head self-attention module. We demonstrate FALIP effectively boosts CLIP zero-shot performance in tasks such as referring expressions comprehension, image classification, and 3D point cloud recognition. Experimental results further show that FALIP outperforms existing methods on most metrics and can augment current methods to enhance their performance.

TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofing

Enhancing the domain generalization performance of Face Anti-Spoofing (FAS) techniques has emerged as a research focus. Existing methods are dedicated to extracting domain-invariant features from various training domains. Despite the promising performance, the extracted features inevitably contain residual style feature bias (e.g., illumination, capture device), resulting in inferior generalization performance. In this paper, we propose an alternative and effective solution, the Textually Guided Domain Generalization (TeG-DG) framework, which can effectively leverage text information for cross-domain alignment. Our core insight is that text, as a more abstract and universal form of expression, can capture the commonalities and essential characteristics across various attacks, bridging the gap between different image domains. Contrary to existing vision-language models, the proposed framework is elaborately designed to enhance the domain generalization ability of the FAS task. Concretely, we first design a Hierarchical Attention Fusion (HAF) module to enable adaptive aggregation of visual features at different levels; Then, a Textual-Enhanced Visual Discriminator (TEVD) is proposed for not only better alignment between the two modalities but also to regularize the classifier with unbiased text features. TeG-DG significantly outperforms previous approaches, especially in situations with extremely limited source domain data (~14% and ~12% improvements on HTER and AUC respectively), showcasing impressive few-shot performance.

A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization

Cross-view geo-localization is a task of matching the same geographic image from different views, e.g., unmanned aerial vehicle (UAV) and satellite. The most difficult challenges are the position shift and the uncertainty of distance and scale. Existing methods are mainly aimed at digging for more comprehensive fine-grained information. However, it underestimates the importance of extracting robust feature representation and the impact of feature alignment. The CNN-based methods have achieved great success in cross-view geo-localization. However it still has some limitations, e.g., it can only extract part of the information in the neighborhood and some scale reduction operations will make some fine-grained information lost. In particular, we introduce a simple and efficient transformer-based structure called Feature Segmentation and Region Alignment (FSRA) to enhance the model's ability to understand contextual information as well as to understand the distribution of instances. Without using additional supervisory information, FSRA divides regions based on the heat distribution of the transformer's feature map, and then aligns multiple specific regions in different views one on one. Finally, FSRA integrates each region into a set of feature representations. The difference is that FSRA does not divide regions manually, but automatically based on the heat distribution of the feature map. So that specific instances can still be divided and aligned when there are significant shifts and scale changes in the image. In addition, a multiple sampling strategy is proposed to overcome the disparity in the number of satellite images and that of images from other sources. Experiments show that the proposed method has superior performance and achieves the state-of-the-art in both tasks of drone view target localization and drone navigation. Code will be released at https://github.com/Dmmm1997/FSRA

Vision-Based UAV Localization System in Denial Environments

Unmanned Aerial Vehicle (UAV) localization capability is critical in a Global Navigation Satellite System (GNSS) denial environment. The aim of this paper is to investigate the problem of locating the UAV itself through a purely visual approach. This task mainly refers to: matching the corresponding geo-tagged satellite images through the images acquired by the camera when the UAV does not acquire GNSS signals, where the satellite images are the bridge between the UAV images and the location information. However, the sampling points of previous cross-view datasets based on UAVs are discrete in spatial distribution and the inter-class relationships are not established. In the actual process of UAV-localization, the inter-class feature similarity of the proximity position distribution should be small due to the continuity of UAV movement in space. In view of this, this paper has reformulated an intensive dataset for UAV positioning tasks, which is named DenseUAV, aiming to solve the problems caused by spatial distance and scale transformation in practical application scenarios, so as to achieve high-precision UAV-localization in GNSS denial environment. In addition, a new continuum-type evaluation metric named SDM is designed to evaluate the accuracy of model matching by exploiting the continuum of UAVs in space. Specifically, with the ideas of siamese networks and metric learning, a transformer-based baseline was constructed to enhance the capture of spatially subtle features. Ultimately, a neighbor-search post-processing strategy was proposed to solve the problem of large distance localisation bias.