Lightweight object detection can promote intelligent robotics to recognize surroundings objects with limited computational resources, and thus receives increasing attention in robotics communities. Recently, high-resolution networks (HRNets) can learn high-resolution representation and it obtains excellent performance as the backbones of current cutting-edge object detectors. However, two crucial issues remain with regard to applying HRNet-based detectors to mobile devices—insufficient local feature interactions and multiscale feature fusion. In this work, we propose a scale-aware squeeze-and-excitation (SASE) module that utilizes SE operations to fully explore feature interactions without increasing network complexity; this is followed by a scale-aware attention (SAA) mechanism, which adaptively fuses multiscale features by estimating the importance of each scale. The SASE module can serve as the basic block for the HRNet, which facilitates the use of HRNet as a backbone for lightweight object detection. Extensive experiments conducted on Microsoft COCO and Pascal VOC demonstrate that the proposed method has a good tradeoff between accuracy and model complexity. With similar numbers of parameters and calculations, the mean average precision (mAP) achieved on the COCO dataset is improved by 3.7% over that of Lite-HRNet.

Multi-label recognition with partial labels (MLR-PL), in which only some labels are known while others are unknown for each image, is a practical task in computer vision, since collecting large-scale and complete multi-label datasets is difficult in real application scenarios. Recently, vision language models (e.g., CLIP) have demonstrated impressive transferability to downstream tasks in data limited or label limited settings. However, current CLIP-based methods suffer from semantic confusion in MLR task due to the lack of fine-grained information in the single global visual and textual representation for all categories. In this work, we address this problem by introducing a semantic decoupling module and a category-specific prompt optimization method in CLIP-based framework. Specifically, the semantic decoupling module following the visual encoder learns category-specific feature maps by utilizing the semantic-guided spatial attention mechanism. Moreover, the category-specific prompt optimization method is introduced to learn text representations aligned with category semantics. Therefore, the prediction of each category is independent, which alleviate the semantic confusion problem. Extensive experiments on Microsoft COCO 2014 and Pascal VOC 2007 datasets demonstrate that the proposed framework significantly outperforms current state-of-art methods with a simpler model structure. Additionally, visual analysis shows that our method effectively separates information from different categories and achieves better performance compared to CLIP-based baseline method.

Deep learning networks are applied for defect detection, among which Cascade R-CNN is a multi-stage object detection network and is state of the art in terms of accuracy and efficiency. However, it is still a challenge for Cascade R-CNN to deal with complex and diverse defects, as the widely varied shapes of defects lead to inefficiency for the traditional convolution filter to extract features. Additionally, the imbalance in features, losses and samples cause lower accuracy. To address the above challenges, this paper proposes a multi-stage balanced R-CNN (MSB R-CNN) for defect detection based on Cascade R-CNN. Firstly, deformable convolution is adopted in different stages of the backbone network to improve its adaptability to the varying shapes of the defect. Then, the features obtained by the backbone network are refined and enhanced by the balanced feature pyramid. To overcome the imbalance of classification and regression loss, the balanced L1 loss is applied at different stages to correct it. Finally, for the sample selection, the interaction of union (IoU) balanced sampler and the online hard example mining (OHEM) sampler are combined at different stages to make the sampling more reasonable, which can bring a better accuracy and convergence effect to the model. The results of our experiments on the DAGM2007 dataset has shown that our network (MSB R-CNN) can achieve a mean average precision (mAP) of 67.5%, an increase of 1.5% mAP, compared to Cascade R-CNN.

Speech-preserving Facial Expression Manipulation (SPFEM) aims to alter facial emotions in video content while preserving the facial movements associated with speech. Current works often fall short due to the inadequate representation of emotion as well as the absence of time-aligned paired data-two corresponding frames from the same speaker that showcase the same speech content but differ in emotional expression. In this work, we introduce a novel framework, Self-Supervised Emotion Representation Disentanglement (SSERD), to disentangle emotion representation for accurate emotion transfer while implementing a paired data construction module to facilitate automated, photorealistic facial animations. Specifically, We developed a module for learning emotion latent codes using StyleGAN's latent space, employing a cross-attention mechanism to extract and predict emotion editing codes, with contrastive learning to differentiate emotions. To overcome the lack of strictly paired data in the SPFEM task, we exploit pretrained StyleGAN to generate paired data, focusing on expression vectors unrelated to mouth shape. Additionally, we employed a hybrid training strategy using both synthetic paired and real unpaired data to enhance the realism of SPFEM model's generated images. Extensive experiments conducted on benchmark datasets, including MEAD and RAVDESS, have validated the effectiveness of our framework, demonstrating its superior capability in generating photorealistic and expressive facial animations.

The paramount challenge in audio-driven One-shot Talking Head Animation (ADOS-THA) lies in capturing subtle imperceptible changes between adjacent video frames. Inherently, the temporal relationship of adjacent audio clips is highly correlated with that of the corresponding adjacent video frames, offering supplementary information that can be pivotal for guiding and supervising talking head animations. In this work, we propose to learn audio-visual correlations and integrate the correlations to help enhance feature representation and regularize final generation by a novel Temporal Audio-Visual Correlation Embedding (TAVCE) framework. Specifically, it first learns an audio-visual temporal correlation metric, ensuring the temporal audio relationships of adjacent clips are aligned with the temporal visual relationships of corresponding adjacent video frames. Since the temporal audio relationship contains aligned information about the visual frame, we first integrate it to guide learning more representative features via a simple yet effective channel attention mechanism. During training, we also use the alignment correlations as an additional objective to supervise generating visual frames. We conduct extensive experiments on several publicly available benchmarks (i.e., HDTF, LRW, VoxCeleb1, and VoxCeleb2) to demonstrate its superiority over existing leading algorithms.

The paramount challenge in audio-driven One-shot Talking Head Animation (ADOS-THA) lies in capturing subtle imperceptible changes between adjacent video frames. Inherently, the temporal relationship of adjacent audio clips is highly correlated with that of the corresponding adjacent video frames, offering supplementary information that can be pivotal for guiding and supervising talking head animations. In this work, we propose to learn audio-visual correlations and integrate the correlations to help enhance feature representation and regularize final generation by a novel Temporal Audio-Visual Correlation Embedding (TAVCE) framework. Specifically, it first learns an audio-visual temporal correlation metric, ensuring the temporal audio relationships of adjacent clips are aligned with the temporal visual relationships of corresponding adjacent video frames. Since the temporal audio relationship contains aligned information about the visual frame, we first integrate it to guide learning more representative features via a simple yet effective channel attention mechanism. During training, we also use the alignment correlations as an additional objective to supervise generating visual frames. We conduct extensive experiments on several publicly available benchmarks (i.e., HDTF, LRW, VoxCeleb1, and VoxCeleb2) to demonstrate its superiority over existing leading algorithms.