Towards End-to-End Explainable Facial Action Unit Recognition via Vision-Language Joint Learning

Facial action units (AUs), as defined in the Facial Action Coding System (FACS), have received significant research interest owing to their diverse range of applications in facial state analysis. Current mainstream FAU recognition models have a notable limitation, i.e., focusing only on the accuracy of AU recognition and overlooking explanations of corresponding AU states. In this paper, we propose an end-to-end Vision-Language joint learning network for explainable FAU recognition (termed VL-FAU), which aims to reinforce AU representation capability and language interpretability through the integration of joint multimodal tasks. Specifically, VL-FAU brings together language models to generate fine-grained local muscle descriptions and distinguishable global face description when optimising FAU recognition. Through this, the global facial representation and its local AU representations will achieve higher distinguishability among different AUs and different subjects. In addition, multi-level AU representation learning is utilised to improve AU individual attention-aware representation capabilities based on multi-scale combined facial stem feature. Extensive experiments on DISFA and BP4D AU datasets show that the proposed approach achieves superior performance over the state-of-the-art methods on most of the metrics. In addition, compared with mainstream FAU recognition methods, VL-FAU can provide local- and global-level interpretability language descriptions with the AUs' predictions.

3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting

In this paper, we propose a novel visual Semantic-Spatial Self-Highlighting Network (termed 3SHNet) for high-precision, high-efficiency and high-generalization image-sentence retrieval. 3SHNet highlights the salient identification of prominent objects and their spatial locations within the visual modality, thus allowing the integration of visual semantics-spatial interactions and maintaining independence between two modalities. This integration effectively combines object regions with the corresponding semantic and position layouts derived from segmentation to enhance the visual representation. And the modality-independence guarantees efficiency and generalization. Additionally, 3SHNet utilizes the structured contextual visual scene information from segmentation to conduct the local (region-based) or global (grid-based) guidance and achieve accurate hybrid-level retrieval. Extensive experiments conducted on MS-COCO and Flickr30K benchmarks substantiate the superior performances, inference efficiency and generalization of the proposed 3SHNet when juxtaposed with contemporary state-of-the-art methodologies. Specifically, on the larger MS-COCO 5K test set, we achieve 16.3%, 24.8%, and 18.3% improvements in terms of rSum score, respectively, compared with the state-of-the-art methods using different image representations, while maintaining optimal retrieval efficiency. Moreover, our performance on cross-dataset generalization improves by 18.6%. Data and code are available at https://github.com/XuriGe1995/3SHNet.

A Bi-Pyramid Multimodal Fusion Method for the Diagnosis of Bipolar Disorders

Previous research on the diagnosis of Bipolar disorder has mainly focused on resting-state functional magnetic resonance imaging. However, their accuracy can not meet the requirements of clinical diagnosis. Efficient multimodal fusion strategies have great potential for applications in multimodal data and can further improve the performance of medical diagnosis models. In this work, we utilize both sMRI and fMRI data and propose a novel multimodal diagnosis model for bipolar disorder. The proposed Patch Pyramid Feature Extraction Module extracts sMRI features, and the spatio-temporal pyramid structure extracts the fMRI features. Finally, they are fused by a fusion module to output diagnosis results with a classifier. Extensive experiments show that our proposed method outperforms others in balanced accuracy from 0.657 to 0.732 on the OpenfMRI dataset, and achieves the state of the art.

SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge

Surgical tool segmentation and action recognition are fundamental building blocks in many computer-assisted intervention applications, ranging from surgical skills assessment to decision support systems. Nowadays, learning-based action recognition and segmentation approaches outperform classical methods, relying, however, on large, annotated datasets. Furthermore, action recognition and tool segmentation algorithms are often trained and make predictions in isolation from each other, without exploiting potential cross-task relationships. With the EndoVis 2022 SAR-RARP50 challenge, we release the first multimodal, publicly available, in-vivo, dataset for surgical action recognition and semantic instrumentation segmentation, containing 50 suturing video segments of Robotic Assisted Radical Prostatectomy (RARP). The aim of the challenge is twofold. First, to enable researchers to leverage the scale of the provided dataset and develop robust and highly accurate single-task action recognition and tool segmentation approaches in the surgical domain. Second, to further explore the potential of multitask-based learning approaches and determine their comparative advantage against their single-task counterparts. A total of 12 teams participated in the challenge, contributing 7 action recognition methods, 9 instrument segmentation techniques, and 4 multitask approaches that integrated both action recognition and instrument segmentation.

Multi-Dimension-Embedding-Aware Modality Fusion Transformer for Psychiatric Disorder Clasification

Deep learning approaches, together with neuroimaging techniques, play an important role in psychiatric disorders classification. Previous studies on psychiatric disorders diagnosis mainly focus on using functional connectivity matrices of resting-state functional magnetic resonance imaging (rs-fMRI) as input, which still needs to fully utilize the rich temporal information of the time series of rs-fMRI data. In this work, we proposed a multi-dimension-embedding-aware modality fusion transformer (MFFormer) for schizophrenia and bipolar disorder classification using rs-fMRI and T1 weighted structural MRI (T1w sMRI). Concretely, to fully utilize the temporal information of rs-fMRI and spatial information of sMRI, we constructed a deep learning architecture that takes as input 2D time series of rs-fMRI and 3D volumes T1w. Furthermore, to promote intra-modality attention and information fusion across different modalities, a fusion transformer module (FTM) is designed through extensive self-attention of hybrid feature maps of multi-modality. In addition, a dimension-up and dimension-down strategy is suggested to properly align feature maps of multi-dimensional from different modalities. Experimental results on our private and public OpenfMRI datasets show that our proposed MFFormer performs better than that using a single modality or multi-modality MRI on schizophrenia and bipolar disorder diagnosis.

Temporal Action Localization with Enhanced Instant Discriminability

Temporal action detection (TAD) aims to detect all action boundaries and their corresponding categories in an untrimmed video. The unclear boundaries of actions in videos often result in imprecise predictions of action boundaries by existing methods. To resolve this issue, we propose a one-stage framework named TriDet. First, we propose a Trident-head to model the action boundary via an estimated relative probability distribution around the boundary. Then, we analyze the rank-loss problem (i.e. instant discriminability deterioration) in transformer-based methods and propose an efficient scalable-granularity perception (SGP) layer to mitigate this issue. To further push the limit of instant discriminability in the video backbone, we leverage the strong representation capability of pretrained large models and investigate their performance on TAD. Last, considering the adequate spatial-temporal context for classification, we design a decoupled feature pyramid network with separate feature pyramids to incorporate rich spatial context from the large model for localization. Experimental results demonstrate the robustness of TriDet and its state-of-the-art performance on multiple TAD datasets, including hierarchical (multilabel) TAD datasets.

Tracker Meets Night: A Transformer Enhancer for UAV Tracking

Most previous progress in object tracking is realized in daytime scenes with favorable illumination. State-of-the-arts can hardly carry on their superiority at night so far, thereby considerably blocking the broadening of visual tracking-related unmanned aerial vehicle (UAV) applications. To realize reliable UAV tracking at night, a spatial-channel Transformer-based low-light enhancer (namely SCT), which is trained in a novel task-inspired manner, is proposed and plugged prior to tracking approaches. To achieve semantic-level low-light enhancement targeting the high-level task, the novel spatial-channel attention module is proposed to model global information while preserving local context. In the enhancement process, SCT denoises and illuminates nighttime images simultaneously through a robust non-linear curve projection. Moreover, to provide a comprehensive evaluation, we construct a challenging nighttime tracking benchmark, namely DarkTrack2021, which contains 110 challenging sequences with over 100 K frames in total. Evaluations on both the public UAVDark135 benchmark and the newly constructed DarkTrack2021 benchmark show that the task-inspired design enables SCT with significant performance gains for nighttime UAV tracking compared with other top-ranked low-light enhancers. Real-world tests on a typical UAV platform further verify the practicability of the proposed approach. The DarkTrack2021 benchmark and the code of the proposed approach are publicly available at https://github.com/vision4robotics/SCT.

ARShoe: Real-Time Augmented Reality Shoe Try-on System on Smartphones

Virtual try-on technology enables users to try various fashion items using augmented reality and provides a convenient online shopping experience. However, most previous works focus on the virtual try-on for clothes while neglecting that for shoes, which is also a promising task. To this concern, this work proposes a real-time augmented reality virtual shoe try-on system for smartphones, namely ARShoe. Specifically, ARShoe adopts a novel multi-branch network to realize pose estimation and segmentation simultaneously. A solution to generate realistic 3D shoe model occlusion during the try-on process is presented. To achieve a smooth and stable try-on effect, this work further develop a novel stabilization method. Moreover, for training and evaluation, we construct the very first large-scale foot benchmark with multiple virtual shoe try-on task-related labels annotated. Exhaustive experiments on our newly constructed benchmark demonstrate the satisfying performance of ARShoe. Practical tests on common smartphones validate the real-time performance and stabilization of the proposed approach.

Real-Time Monocular Human Depth Estimation and Segmentation on Embedded Systems

Estimating a scene's depth to achieve collision avoidance against moving pedestrians is a crucial and fundamental problem in the robotic field. This paper proposes a novel, low complexity network architecture for fast and accurate human depth estimation and segmentation in indoor environments, aiming to applications for resource-constrained platforms (including battery-powered aerial, micro-aerial, and ground vehicles) with a monocular camera being the primary perception module. Following the encoder-decoder structure, the proposed framework consists of two branches, one for depth prediction and another for semantic segmentation. Moreover, network structure optimization is employed to improve its forward inference speed. Exhaustive experiments on three self-generated datasets prove our pipeline's capability to execute in real-time, achieving higher frame rates than contemporary state-of-the-art frameworks (114.6 frames per second on an NVIDIA Jetson Nano GPU with TensorRT) while maintaining comparable accuracy.

FastHand: Fast Hand Pose Estimation From A Monocular Camera

Hand gesture recognition constitutes the initial step in most methods related to human-robot interaction. There are two key challenges in this task. The first one corresponds to the difficulty of achieving stable and accurate hand landmark predictions in real-world scenarios, while the second to the decreased time of forward inference. In this paper, we propose a fast and accurate framework for hand pose estimation, dubbed as "FastHand". Using a lightweight encoder-decoder network architecture, we achieve to fulfil the requirements of practical applications running on embedded devices. The encoder consists of deep layers with a small number of parameters, while the decoder makes use of spatial location information to obtain more accurate results. The evaluation took place on two publicly available datasets demonstrating the improved performance of the proposed pipeline compared to other state-of-the-art approaches. FastHand offers high accuracy scores while reaching a speed of 25 frames per second on an NVIDIA Jetson TX2 graphics processing unit.