Skeleton-based action recognition is a central task of human-computer interaction. Current methods apply the modeling paradigm of image recognition to it directly. However, the skeleton sequences abstracted from the human body is a sparse representation. The features extracted from the skeleton encoder are spatiotemporal decoupled, which may confuse the semantics. To reduce the coupling and improve the semantics of the global features, we propose a framework (STD-CL) for skeleton-based action recognition. We first decouple the spatial-specific and temporal-specific features from the spatiotemporal features. Then we apply the attentive features to contrastive learning, which pulls together the features from the positive pairs and pushes away the feature embedding from the negative pairs. Moreover, the proposed training strategy STD-CL can be incorporated into current methods. Without additional compute consumption in the testing phase, our STD-CL with four various backbones (HCN, 2S-AGCN, CTR-GCN, and Hyperformer) achieves improvement on NTU60, NTU120, and NW-UCLA benchmarks. We will release our code at: https://github.com/BUPTSJZhang/STD-CL.
Recent advances in text-to-image generators have led to substantial capabilities in image generation. However, the complexity of prompts acts as a bottleneck in the quality of images generated. A particular under-explored facet is the ability of generative models to create high-quality images comprising multiple components given as a prior. In this paper, we propose and validate a metric called Components Inclusion Score (CIS) to evaluate the extent to which a model can correctly generate multiple components. Our results reveal that the evaluated models struggle to incorporate all the visual elements from prompts with multiple components (8.53% drop in CIS per component for all evaluated models). We also identify a significant decline in the quality of the images and context awareness within an image as the number of components increased (15.91% decrease in inception Score and 9.62% increase in Frechet Inception Distance). To remedy this issue, we fine-tuned Stable Diffusion V2 on a custom-created test dataset with multiple components, outperforming its vanilla counterpart. To conclude, these findings reveal a critical limitation in existing text-to-image generators, shedding light on the challenge of generating multiple components within a single image using a complex prompt.
Large pre-trained vision models achieve impressive success in computer vision. However, fully fine-tuning large models for downstream tasks, particularly in video understanding, can be prohibitively computationally expensive. Recent studies turn their focus towards efficient image-to-video transfer learning. Nevertheless, existing efficient fine-tuning methods lack attention to training memory usage and exploration of transferring a larger model to the video domain. In this paper, we present a novel Spatial-Temporal Side Network for memory-efficient fine-tuning large image models to video understanding, named Side4Video. Specifically, we introduce a lightweight spatial-temporal side network attached to the frozen vision model, which avoids the backpropagation through the heavy pre-trained model and utilizes multi-level spatial features from the original image model. Extremely memory-efficient architecture enables our method to reduce 75% memory usage than previous adapter-based methods. In this way, we can transfer a huge ViT-E (4.4B) for video understanding tasks which is 14x larger than ViT-L (304M). Our approach achieves remarkable performance on various video datasets across unimodal and cross-modal tasks (i.e., action recognition and text-video retrieval), especially in Something-Something V1&V2 (67.3% & 74.6%), Kinetics-400 (88.6%), MSR-VTT (52.3%), MSVD (56.1%) and VATEX (68.8%). We release our code at https://github.com/HJYao00/Side4Video.
Local Binary Patterns (LBP) are extensively used to analyze local texture features of an image. Several new extensions to LBP-based texture descriptors have been proposed, focusing on improving noise robustness by using different coding or thresholding schemes. In this paper we propose three algorithms (LBP), Shift Local Binary Pattern (SLBP), and Multi Shift Local Binary Pattern (MSLBP),to extract features for palmprint images that help to obtain the best unique and characteristic values of an image for identification. The Principal Component Analysis (PCA) algorithm has been applied to reduce the size of the extracted feature matrix in random space and in the matching process; the Linear Discriminant Analysis (LDA) algorithm is used. Several experiments were conducted on the large multispectral database (blue, green, red, and infrared) of the University of Hong Kong. As result, distinguished and high results were obtained where it was proved that, the blue spectrum is superior to all spectra perfectly.
Adversarial attacks involve adding perturbations to the source image to cause misclassification by the target model, which demonstrates the potential of attacking face recognition models. Existing adversarial face image generation methods still can't achieve satisfactory performance because of low transferability and high detectability. In this paper, we propose a unified framework Adv-Diffusion that can generate imperceptible adversarial identity perturbations in the latent space but not the raw pixel space, which utilizes strong inpainting capabilities of the latent diffusion model to generate realistic adversarial images. Specifically, we propose the identity-sensitive conditioned diffusion generative model to generate semantic perturbations in the surroundings. The designed adaptive strength-based adversarial perturbation algorithm can ensure both attack transferability and stealthiness. Extensive qualitative and quantitative experiments on the public FFHQ and CelebA-HQ datasets prove the proposed method achieves superior performance compared with the state-of-the-art methods without an extra generative model training process. The source code is available at https://github.com/kopper-xdu/Adv-Diffusion.
Text-to-Image (T2I) diffusion models have gained popularity recently due to their multipurpose and easy-to-use nature, e.g. image and video generation as well as editing. However, training a diffusion model specifically for 3D scene editing is not straightforward due to the lack of large-scale datasets. To date, editing 3D scenes requires either re-training the model to adapt to various 3D edited scenes or design-specific methods for each special editing type. Furthermore, state-of-the-art (SOTA) methods require multiple synchronized edited images from the same scene to facilitate the scene editing. Due to the current limitations of T2I models, it is very challenging to apply consistent editing effects to multiple images, i.e. multi-view inconsistency in editing. This in turn compromises the desired 3D scene editing performance if these images are used. In our work, we propose a novel training-free 3D scene editing technique, Free-Editor, which allows users to edit 3D scenes without further re-training the model during test time. Our proposed method successfully avoids the multi-view style inconsistency issue in SOTA methods with the help of a "single-view editing" scheme. Specifically, we show that editing a particular 3D scene can be performed by only modifying a single view. To this end, we introduce an Edit Transformer that enforces intra-view consistency and inter-view style transfer by utilizing self- and cross-attention, respectively. Since it is no longer required to re-train the model and edit every view in a scene, the editing time, as well as memory resources, are reduced significantly, e.g., the runtime being $\sim \textbf{20} \times$ faster than SOTA. We have conducted extensive experiments on a wide range of benchmark datasets and achieve diverse editing capabilities with our proposed technique.
Deep learning models trained with large amounts of data have become a recent and effective approach to predictive problem solving -- these have become known as "foundation models" as they can be used as fundamental tools for other applications. While the paramount examples of image classification (earlier) and large language models (more recently) led the way, the Segment Anything Model (SAM) was recently proposed and stands as the first foundation model for image segmentation, trained on over 10 million images and with recourse to over 1 billion masks. However, the question remains -- what are the limits of this foundation? Given that magnetic resonance imaging (MRI) stands as an important method of diagnosis, we sought to understand whether SAM could be used for a few tasks of zero-shot segmentation using MRI data. Particularly, we wanted to know if selecting masks from the pool of SAM predictions could lead to good segmentations. Here, we provide a critical assessment of the performance of SAM on magnetic resonance imaging data. We show that, while acceptable in a very limited set of cases, the overall trend implies that these models are insufficient for MRI segmentation across the whole volume, but can provide good segmentations in a few, specific slices. More importantly, we note that while foundation models trained on natural images are set to become key aspects of predictive modelling, they may prove ineffective when used on other imaging modalities.
Recently, diffusion models (DMs) have become the state-of-the-art method for image synthesis. Editing models based on DMs, known for their high fidelity and precision, have inadvertently introduced new challenges related to image copyright infringement and malicious editing. Our work is the first to formalize and address this issue. After assessing and attempting to enhance traditional image watermarking techniques, we recognize their limitations in this emerging context. In response, we develop a novel technique, RIW (Robust Invisible Watermarking), to embed invisible watermarks leveraging adversarial example techniques. Our technique ensures a high extraction accuracy of $96\%$ for the invisible watermark after editing, compared to the $0\%$ offered by conventional methods. We provide access to our code at https://github.com/BennyTMT/RIW.
The quest for accurate prediction of drug molecule properties poses a fundamental challenge in the realm of Artificial Intelligence Drug Discovery (AIDD). An effective representation of drug molecules emerges as a pivotal component in this pursuit. Contemporary leading-edge research predominantly resorts to self-supervised learning (SSL) techniques to extract meaningful structural representations from large-scale, unlabeled molecular data, subsequently fine-tuning these representations for an array of downstream tasks. However, an inherent shortcoming of these studies lies in their singular reliance on one modality of molecular information, such as molecule image or SMILES representations, thus neglecting the potential complementarity of various molecular modalities. In response to this limitation, we propose MolIG, a novel MultiModaL molecular pre-training framework for predicting molecular properties based on Image and Graph structures. MolIG model innovatively leverages the coherence and correlation between molecule graph and molecule image to execute self-supervised tasks, effectively amalgamating the strengths of both molecular representation forms. This holistic approach allows for the capture of pivotal molecular structural characteristics and high-level semantic information. Upon completion of pre-training, Graph Neural Network (GNN) Encoder is used for the prediction of downstream tasks. In comparison to advanced baseline models, MolIG exhibits enhanced performance in downstream tasks pertaining to molecular property prediction within benchmark groups such as MoleculeNet Benchmark Group and ADMET Benchmark Group.
Curation methods for massive vision-language datasets trade off between dataset size and quality. However, even the highest quality of available curated captions are far too short to capture the rich visual detail in an image. To show the value of dense and highly-aligned image-text pairs, we collect the Densely Captioned Images (DCI) dataset, containing 8012 natural images human-annotated with mask-aligned descriptions averaging above 1000 words each. With precise and reliable captions associated with specific parts of an image, we can evaluate vision-language models' (VLMs) understanding of image content with a novel task that matches each caption with its corresponding subcrop. As current models are often limited to 77 text tokens, we also introduce a summarized version (sDCI) in which each caption length is limited. We show that modern techniques that make progress on standard benchmarks do not correspond with significant improvement on our sDCI based benchmark. Lastly, we finetune CLIP using sDCI and show significant improvements over the baseline despite a small training set. By releasing the first human annotated dense image captioning dataset, we hope to enable the development of new benchmarks or fine-tuning recipes for the next generation of VLMs to come.