Due to the difficulty of acquiring large-scale 3D human keypoint annotation, previous methods for 3D human pose estimation (HPE) have often relied on 2D image features and sequential 2D annotations. Furthermore, the training of these networks typically assumes the prediction of a human bounding box and the accurate alignment of 3D point clouds with 2D images, making direct application in real-world scenarios challenging. In this paper, we present the 1stframework for end-to-end 3D human pose estimation, named LPFormer, which uses only LiDAR as its input along with its corresponding 3D annotations. LPFormer consists of two stages: firstly, it identifies the human bounding box and extracts multi-level feature representations, and secondly, it utilizes a transformer-based network to predict human keypoints based on these features. Our method demonstrates that 3D HPE can be seamlessly integrated into a strong LiDAR perception network and benefit from the features extracted by the network. Experimental results on the Waymo Open Dataset demonstrate the state-of-the-art performance, and improvements even compared to previous multi-modal solutions.

There is a recent need in the LiDAR perception field for unifying multiple tasks in a single strong network with improved performance, as opposed to using separate networks for each task. In this paper, we introduce a new LiDAR multi-task learning paradigm based on the transformer. The proposed LiDARFormer utilizes cross-space global contextual feature information and exploits cross-task synergy to boost the performance of LiDAR perception tasks across multiple large-scale datasets and benchmarks. Our novel transformer-based framework includes a cross-space transformer module that learns attentive features between the 2D dense Bird’s Eye View (BEV) and 3D sparse voxel feature maps. Additionally, we propose a transformer decoder for the segmentation task to dynamically adjust the learned features by leveraging the categorical feature representations. Furthermore, we combine the segmentation and detection features in a shared transformer decoder with cross-task attention layers to enhance and integrate the object-level and class-level features. LiDARFormer is evaluated on the large-scale nuScenes and the Waymo Open datasets for both 3D detection and semantic segmentation tasks, and it achieves state-of-the-art performance on both tasks.

Passive RFID has the advantages of rapid identification of multi-target objects and low implementation cost. It is the most critical technology in the Industrial Internet of Things information-gathering layer and is extensively applied in various industries, such as smart production, asset management, and monitoring. The signal collision caused by the communication between the reader/writer and tags sharing the same wireless channel has caused a series of problems, such as the reduction of the identification efficiency of the reader/writer and the increment of the missed reading rate, thus restricting the further development of RFID. At present, many hybrid anti-collision algorithms integrate the advantages of Aloha and TS algorithms to optimize RFID system performance, but these solutions also suffer from performance bottlenecks. In order to break through such performance bottleneck, based on the ISE-BS algorithm, we combined the sub-frame observation mechanism and the Q value adjustment strategy and proposed two hybrid anti-collision algorithms. The experimental results show that the two algorithms proposed in this paper have obvious advantages in system throughput, time efficiency and other metrics, surpassing existing UHF RFID anti-collision algorithms.

LiDAR-based 3D object detection, semantic segmentation, and panoptic segmentation are usually implemented in specialized networks with distinctive architectures that are difficult to adapt to each other. This paper presents LidarMultiNet, a LiDAR-based multi-task network that unifies these three major LiDAR perception tasks. Among its many benefits, a multi-task network can reduce the overall cost by sharing weights and computation among multiple tasks. However, it typically underperforms compared to independently combined single-task models. The proposed LidarMultiNet aims to bridge the performance gap between the multi-task network and multiple single-task networks. At the core of LidarMultiNet is a strong 3D voxel-based encoder-decoder architecture with a Global Context Pooling (GCP) module extracting global contextual features from a LiDAR frame. Task-specific heads are added on top of the network to perform the three LiDAR perception tasks. More tasks can be implemented simply by adding new task-specific heads while introducing little additional cost. A second stage is also proposed to refine the first-stage segmentation and generate accurate panoptic segmentation results. LidarMultiNet is extensively tested on both Waymo Open Dataset and nuScenes dataset, demonstrating for the first time that major LiDAR perception tasks can be unified in a single strong network that is trained end-to-end and achieves state-of-the-art performance. Notably, LidarMultiNet reaches the official 1 place in the Waymo Open Dataset 3D semantic segmentation challenge 2022 with the highest mIoU and the best accuracy for most of the 22 classes on the test set, using only LiDAR points as input. It also sets the new state-of-the-art for a single model on the Waymo 3D object detection benchmark and three nuScenes benchmarks.

Fine-grained Visual Classification (FGVC), which aims to identify objects from subcategories, presents great challenges for classification due to large intra-class differences and subtle inter-class differences. To address these issues of FGVC, this paper proposes a patch selection model referenced from CLIP for Fine Grained Visual Classification, namely CLIP-FG. Specifically, unlike the previous CLIP, which focused only on the level of text and image, we calculate the similarity between labels and image patches. Top k image patches are selected and their indexes fed into the Vision Transformer to select discriminative areas to improve the performance of fine grained image classification. Quantitative evaluations show CLIP-FG’s competitive performance against mainstream methods.

Answer ranking is an important task in Community Question Answering (CQA), by which “Good” answers should be ranked in the front of “Bad” or “Potentially Useful” answers. The state of the art is the attention-based classification framework that learns the mapping between the questions and the answers. However, we observe that existing attention-based methods perform poorly on complicated question-answer pairs. One major reason is that existing methods cannot get accurate alignments between questions and answers for such pairs. We call the phenomenon “attention divergence”. In this paper, we propose a new attention mechanism, called Focusing Attention Network(FAN), which can automatically draw back the divergent attention by adding the semantic, and metadata features. Our Model can focus on the most important part of the sentence and therefore improve the answer ranking performance. Experimental results on the CQA dataset of SemEval-2016 and SemEval-2017 demonstrate that our method respectively attains 79.38 and 88.72 on MAP and outperforms the Top-1 system in the shared task by 0.19 and 0.29.