Monocular 3D object detection (Mono3D) holds noteworthy promise for autonomous driving applications owing to the cost-effectiveness and rich visual context of monocular camera sensors. However, depth ambiguity poses a significant challenge, as it requires extracting precise 3D scene geometry from a single image, resulting in suboptimal performance when transferring knowledge from a LiDARbased teacher model to a camera-based student model. To facilitate effective distillation, we introduce Monocular Teaching Assistant Knowledge Distillation (MonoTAKD), which proposes a camera-based teaching assistant (TA) model to transfer robust 3D visual knowledge to the student model, leveraging the smaller feature representation gap. Additionally, we define 3D spatial cues as residual features that capture the differences between the teacher and the TA models. We then leverage these cues to improve the student model's 3D perception capabilities. Experimental results show that our MonoTAKD achieves state-of-the-art performance on the KITTI3D dataset. Furthermore, we evaluate the performance on nuScenes and KITTI raw datasets to demonstrate the generalization of our model to multi-view 3D and unsupervised data settings. Our code is available at https://github.com/hoiliu-0801/MonoTAKD.

Vision Transformers (ViTs) have emerged as the backbone of many segmentation models, consistently achieving state-of-the-art (SOTA) performance. However, their success comes at a significant computational cost. Image token pruning is one of the most effective strategies to address this complexity. However, previous approaches fall short when applied to more complex task-oriented segmentation (TOS), where the class of each image patch is not predefined but dependent on the specific input task. This work introduces the Vision Language Guided Token Pruning (VLTP), a novel token pruning mechanism that can accelerate ViT-based segmentation models, particularly for TOS guided by multi-modal large language model (MLLM). We argue that ViT does not need to process every image token through all of its layers—only the tokens related to reasoning tasks are necessary. We design a new pruning decoder to take both image tokens and vision-language guidance as input to predict the relevance of each image token to the task. Only image tokens with high relevance are passed to deeper layers of the ViT. Experiments show that the VLTP framework reduces the computational costs of ViT by approximately 25% without performance degradation and by around 40% with only a 1% performance drop. The code associated with this study can be found at this URL.

The applications of large language models (LLMs) have expanded well beyond the confines of text processing, signaling a new era where LLMs are envisioned as generalist agents capable of operating within complex environments.These environments are often highly expansive, making it impossible for the LLM to process them within its short-term memory.Motivated by recent research on extending the capabilities of LLMs with tools, we seek to investigate the intriguing potential of tools to augment LLMs in handling such complexity by introducing a novel class of tools, termed middleware, to aid in the proactive exploration within these massive environments.Such specialized tools can serve as a middleware layer shielding the LLM from environmental complexity.In two representative complex environmentsknowledge bases (KBs) and databases-we demonstrate the significant potential of augmenting language agents with tools in complex environments.Notably, equipped with the middleware, GPT-4 achieves 2.8× the performance of the best baseline in tasks requiring access to database content and 2.2× in KB tasks.Our findings illuminate the path for advancing language agents in real-world applications.1

In recent times, a plethora of hardware accelerators has emerged, catering to graph learning applications. However, the focus has primarily been on accelerating graph analysis, graph clustering, and graph mining, with a lack of attention to knowledge graph reasoning. Graph reasoning requires a more complex model to handle the complicated knowledge graph compared to other graph learning tasks. A primary knowledge graph reasoning task is to find the implicit relations between entities of a given knowledge graph, which demands a significantly longer training time than traditional graph learning algorithms due to the model complexity. Therefore, it is essential to develop an acceleration method to mitigate the training cost for the practical deployment of this task. Prior work in this field has solely considered using a single GPU or distributed GPU cluster to accelerate translational embedding models. However, as demonstrated in this paper, such general-purpose GPUs don't provide satisfactory results for more complex reinforcement learning-based models. Hence, it becomes necessary to design customized domain-specific accelerators. This work proposes GraFlex, the first domain specific accelerator for reinforcement learning-based knowledge graph reasoning, implemented on FPGA. We first develop a compression method for knowledge graphs. Then, we explore FPGAs of different sizes, analyze their on-chip resources, and suggest a mechanism to achieve high-speed training on devices with insufficient resources using the aforementioned compression method.

Robust perception is a vital component for ensuring safe autonomous driving. Automotive radar (77 to 81 GHz) offering weather-resilient sensing provides a complementary capability to the vision-or LiDAR-based autonomous driving systems. Raw radio-frequency (RF) radar tensors contain rich spatiotemporal semantics besides 3D location information. Most previous methods take in 3D (Doppler-range-azimuth) RF radar tensors, allowing prediction of an object’s location, heading angle, and size in bird’s-eye-view (BEV). However, they lack the ability to simultaneously infer objects’ size, orientation, and identity in the 3D space. To overcome this limitation, we propose a joint architecture, called CenterRadarNet, designed to facilitate high-resolution representation learning from 4D (Doppler-range-azimuth-elevation) radar data for 3D object detection and re-identification (reID) tasks. Moreover, we build an online tracker utilizing the learned appearance embedding for re-ID. CenterRadarNet achieves the state-of-the-art result on the K-Radar 3D object detection benchmark. In addition, we present the first 3D object-tracking result on the K-Radar dataset. CenterRadarNet shows consistent, robust performance in diverse driving scenarios, emphasizing its wide applicability. Code is available at: https://github.com/Andy-Cheng/CenterRadarNet

This paper addresses challenges in monitoring human behavior in crowds through floor vibration sensing, overcoming limitations like subjective manual observation, visual occlusions, and audio interference. Our approach involves tackling limited-data vibration signal tasks by conducting pre-training across modalities, leveraging publicly available audio datasets. By leveraging self-supervised representation learning to pre-train on publicly available audio datasets, our approach reduces data requirements, improves robustness, and minimizes the need for human labeling efforts. Evaluation using in-game stadium vibration data with YouTube audio dataset demonstrates up to 5.8 × error reduction for crowd behavior.

In the domain of autonomous driving, the integration of multi-modal perception techniques based on data from diverse sensors has demonstrated substantial progress. Effectively surpassing the capabilities of state-of-the-art single-modality detectors through sensor fusion remains an active challenge. This work leverages the respective advantages of cameras in perspective view and radars in Bird’s Eye View (BEV) to greatly enhance overall detection and tracking performance. Our approach, Camera-Radar Associated Fusion Tracking Booster (CRAFTBooster) represents a pioneering effort to enhance radar-camera fusion in the tracking stage, contributing to improved 3D MOT accuracy. The superior experimental results on K-Radaar dataset, which exhibit 5-6% on IDF1 tracking performance gain, validate the potential of effective sensor fusion in advancing autonomous driving.

The increasing popularity of virtual reality (VR) has stressed the importance of authenticating VR users while preserving their privacy. Behavioral biometrics, owing to their robustness and ease of collection, compared to traditional modes such as passwords, have become a favored authentication choice. While current approaches that utilize behavioral biometrics to train classifiers for authentication yield promising accuracy, they cause privacy breaches by sharing sensitive data with a server to train a central model. In this paper, we present MetaFL, a first-of-its-kind privacy-preserving VR authentication framework that leverages federated learning (FL) on multi-modal motion data. The design of MetaFL is motivated by our key insight that various modalities of motion data uniquely affect authentication performance for individual users and among different users. It is attributed to the fundamental challenge of privacy-preserving user authentication: users can access only their own data with limited global knowledge. To tackle this issue, MetaFL judiciously selects the most suitable modalities for each user, which is decomposed into within-user ordering and between-user selection to eliminate the complex interplay between various conflicting factors. Moreover, we develop a personalized strategy to initialize FL models, further improving authentication accuracy. Our extensive performance evaluation on six public datasets shows that MetaFL outperforms state-of-the-art FL-based models (e.g., 17--28% higher authentication accuracy), and its accuracy gap with the non-privacy-preserving central model is small (i.e., only <2%).

Well-trained deep neural networks (DNNs) treat all test samples equally during prediction. Adaptive DNN inference with early exiting leverages the observation that some test examples can be easier to predict than others. This paper presents EENet, a novel early-exiting scheduling framework for multi-exit DNN models. Instead of having every sample go through all DNN layers during prediction, EENet learns an early exit scheduler, which can intelligently terminate the inference earlier for certain predictions, which the model has high confidence of early exit. As opposed to previous early-exiting solutions with heuristics-based methods, our EENet framework optimizes an early-exiting policy to maximize model accuracy while satisfying the given per-sample average inference budget. Extensive experiments are conducted on four computer vision datasets (CIFAR-10, CIFAR-100, ImageNet, Cityscapes) and two NLP datasets (SST-2, AgNews). The results demonstrate that the adaptive inference by EENet can outperform the representative existing early exit techniques. We also perform a detailed visualization analysis of the comparison results to interpret the benefits of EENet.

Container security has received much research attention recently. Previous work has proposed to apply various machine learning techniques to detect security attacks in containerized applications. On one hand, supervised machine learning schemes require sufficient labeled training data to achieve good attack detection accuracy. On the other hand, unsupervised machine learning methods are more practical by avoiding training data labeling requirements, but they often suffer from high false alarm rates. In this article, we present a generic self-supervised hybrid learning (SHIL) framework for achieving efficient online security attack detection in containerized systems. SHIL can effectively combine both unsupervised and supervised learning algorithms but does not require any manual data labeling. We have implemented a prototype of SHIL and conducted experiments over 46 real-world security attacks in 29 commonly used server applications. Our experimental results show that SHIL can reduce false alarms by 33%–93% compared to existing supervised, unsupervised, or semi-supervised machine learning schemes while achieving a higher or similar detection rate.

Knowledge graph (KG) link prediction aims to infer new facts based on existing facts in the KG. Recent studies have shown that using the graph neighborhood of a node via graph neural networks (GNNs) provides more useful information compared to just using the query information. Conventional GNNs for KG link prediction follow the standard message-passing paradigm on the entire KG, which leads to superfluous computation, over-smoothing of node representations, and also limits their expressive power. On a large scale, it becomes computationally expensive to aggregate useful information from the entire KG for inference. To address the limitations of existing KG link prediction frameworks, we propose a novel retrieve-and-read framework, which first retrieves a relevant subgraph context for the query and then jointly reasons over the context and the query with a high-capacity reader. As part of our exemplar instantiation for the new framework, we propose a novel Transformer-based GNN as the reader, which incorporates graph-based attention structure and cross-attention between query and context for deep fusion. This simple yet effective design enables the model to focus on salient context information relevant to the query. Empirical results on two standard KG link prediction datasets demonstrate the competitive performance of the proposed method. Furthermore, our analysis yields valuable insights for designing improved retrievers within the framework.

In this paper, we propose EdgeHD, a hierarchy-aware learning solution that performs online training and inference in a highly distributed, cost-effective way. We use brain-inspired hyperdimensional (HD) computing as the key enabler. HD computing performs the computation tasks on a high-dimensional space to emulate functionalities of the human memory, such as inter-data relationship reasoning and information aggregation. EdgeHD exploits HD computing to effectively learn the classification models on individual devices and combine the models through the hierarchical IoT nodes without high communication costs. We also propose a hardware design that accelerates EdgeHD on low-power FPGA platforms. We evaluated EdgeHD for a wide range of real-world classification applications. The evaluation shows that EdgeHD provides highly efficient computation with reduced communication. For example, EdgeHD achieves on average$3.4\times$and$11.7\times (1.9\times$and$7.8\times$) speedup and energy efficiency improvement during the training (inference) as compared to the centralized learning approach. It reduces the communication costs by 85% for the training and 78% for the inference.

Heart rate is a critical metric for human cardiovascular health. Most common methods for measuring human heart rate involve wearable devices (e.g., electrocardiography, smart watches). However, such devices can cause discomfort to some patients, especially the elderly or young children. This paper presents FreePulse, a heart rate monitoring system for seated subjects using ambient vibrations. FreePulse builds on our past work using vibrations in the building structures around us to measure human activities and health. As people’s hearts beat, they push on the surfaces the body is touching, creating vibrations in those structures. We combine structure response characterization with human pulse modelling to identify these pulse-induced vibrations from ambient vibration. In testing, FreePulse has shown up to 96% pulse rate accuracy on average, competitive with consumer-grade wearable devices.

In this paper, we propose a Hyper-Dimensional genome analysis platform. Instead of working with original sequences, our method maps the genome sequences into high-dimensional space and performs sequence matching with simple and parallel similarity searches. At the algorithm level, we revisit the sequence searching with brain-like memorization that Hyper-Dimensional computing natively supports. Instead of working on the original data, we map all data points into high-dimensional space, enabling the main sequence searching operations to process in a hardware-friendly way. We accordingly design a density-aware FPGA implementation. Our solution searches the similarity of an encoded query and large-scale genome library through different chunks. We exploit the holographic representation of patterns to stop search operations on libraries with a lower chance of a match. This translates our computation from dense to highly sparse just after a few chuck-based searches. Our evaluation shows that our accelerator can provide 46× speedup and 188× energy efficiency improvement compared to a state-of-the-art GPU implementation. Results show that our accelerator achieves up to 3440.6 GCUPS using a single Xilinx Alveo U280 board.

People can easily imagine the potential sound while seeing an event. This natural synchronization between audio and visual signals reveals their intrinsic correlations. To this end, we propose to learn the audio-visual correlations from the perspective of cross-modal generation in a self-supervised manner, the learned correlations can be then readily applied in multiple downstream tasks such as the audio-visual cross-modal localization and retrieval. We introduce a novel Variational AutoEncoder (VAE) framework that consists of Multiple encoders and a Shared decoder (MS-VAE) with an additional Wasserstein distance constraint to tackle the problem. Extensive experiments demonstrate that the optimized latent representation of the proposed MS-VAE can effectively learn the audio-visual correlations and can be readily applied in multiple audio-visual downstream tasks to achieve competitive performance even without any given label information during training.

Cross-view video synthesis task seeks to generate video sequences of one view from another dramatically different view. In this paper, we investigate the exocentric (third-person) view to egocentric (first-person) view video generation task. This is challenging because egocentric view sometimes is remarkably different from the exocentric view. Thus, transforming the appearances across the two different views is a non-trivial task. Particularly, we propose a novel Bi-directional Spatial Temporal Attention Fusion Generative Adversarial Network (STA-GAN) to learn both spatial and temporal information to generate egocentric video sequences from the exocentric view. The proposed STA-GAN consists of three parts: temporal branch, spatial branch, and attention fusion. First, the temporal and spatial branches generate a sequence of fake frames and their corresponding features. The fake frames are generated in both downstream and upstream directions for both temporal and spatial branches. Next, the generated four different fake frames and their corresponding features (spatial and temporal branches in two directions) are fed into a novel multi-generation attention fusion module to produce the final video sequence. Meanwhile, we also propose a novel temporal and spatial dual-discriminator for more robust network optimization. Extensive experiments on the Side2Ego and Top2Ego datasets show that the proposed STA-GAN significantly outperforms the existing methods.

Cross-view image generation has been recently proposed to generate images of one view from another dramatically different view. In this paper, we investigate exocentric (third-person) view to egocentric (first-person) view image generation. This is a challenging task since egocentric view sometimes is remarkably different from exocentric view. Thus, transforming the appearances across the two views is a nontrivial task. To this end, we propose a novel Parallel Generative Adversarial Network (P-GAN) with a novel cross-cycle loss to learn the shared information for generating egocentric images from exocentric view. We also incorporate a novel contextual feature loss in the learning procedure to capture the contextual information in images. Extensive experiments on the Exo-Ego datasets [1] show that our model outperforms the state-of-the-art approaches.

Recently, there has been a growing interest in wearable sensors which provides new research perspectives for 360 ° video analysis. However, the lack of 360 ° datasets in literature hinders the research in this field. To bridge this gap, in this paper we propose a novel Egocentric (first-person) 360° Kinetic human activity video dataset (EgoK360). The EgoK360 dataset contains annotations of human activity with different sub-actions, e.g., activity Ping-Pong with four sub-actions which are pickup-ball, hit, bounce-ball and serve. To the best of our knowledge, EgoK360 is the first dataset in the domain of first-person activity recognition with a 360° environmental setup, which will facilitate the egocentric 360 ° video understanding. We provide experimental results and comprehensive analysis of variants of the two-stream network for 360 egocentric activity recognition. The EgoK360 dataset can be downloaded from https://egok360.github.io/.

Since we were babies, we intuitively develop the ability to correlate the input from different cognitive sensors such as vision, audio, and text. However, in machine learning, this cross-modal learning is a nontrivial task because different modalities have no homogeneous properties. Previous works discover that there should be bridges among different modalities. From a neurology and psychology perspective, humans have the capacity to link one modality with another one, e.g., associating a picture of a bird with the only hearing of its singing and vice versa. Is it possible for machine learning algorithms to recover the scene given the audio signal? In this paper, we propose a novel Cascade Attention-Guided Residue GAN (CAR-GAN), aiming at reconstructing the scenes given the corresponding audio signals. Particularly, we present a residue module to mitigate the gap between different modalities progressively. Moreover, a cascade attention guided network with a novel classification loss function is designed to tackle the cross-modal learning task. Our model keeps consistency in the high-level semantic label domain and is able to balance two different modalities. The experimental results demonstrate that our model achieves the state-of-the-art cross-modal audio-visual generation on the challenging Sub-URMP dataset.