arXiv subjects

Hang Guo

Publications and source records attributed to Hang Guo.

42 records · Page 3Linked to original sources

arXiv2024

Remember and Recall: Associative-Memory-based Trajectory Prediction

Trajectory prediction is a pivotal component of autonomous driving systems, enabling the application of accumulated movement experience to current scenarios. Although most existing methods concentrate on learning continuous representations to gain valuable experience, they often suffer from computational inefficiencies and struggle with unfamiliar situations. To address this issue, we propose the Fragmented-Memory-based Trajectory Prediction (FMTP) model, inspired by the remarkable learning capabilities of humans, particularly their ability to leverage accumulated experience and recall relevant memories in unfamiliar situations. The FMTP model employs discrete representations to enhance computational efficiency by reducing information redundancy while maintaining the flexibility to utilize past experiences. Specifically, we design a learnable memory array by consolidating continuous trajectory representations from the training set using defined quantization operations during the training phase. This approach further eliminates redundant information while preserving essential features in discrete form. Additionally, we develop an advanced reasoning engine based on language models to deeply learn the associative rules among these discrete representations. Our method has been evaluated on various public datasets, including ETH-UCY, inD, SDD, nuScenes, Waymo, and VTL-TP. The extensive experimental results demonstrate that our approach achieves significant performance and extracts more valuable experience from past trajectories to inform the current state.

cs.CV↗

arXiv2023

High-Performance and Low-Power Sub-5 nm Field-Effect Transistors Based on 7-9-7-AGNR

Recently, an extremely-air-stable one-dimensional 7-9-7-AGNR was successfully fabricated. To further reveal its potential application in sub-5-nm field-effect transistors (FETs), there is an urgent need to develop integrated circuits. Here, we report first-principles quantum-transport simulations on the performance limits of n- and p-type sub-5-nm one-dimensional 7-9-7-AGNR FET. We find that the on-state current (Ion) in 7-9-7-AGNR FET can be effectively manipulated by the length of the gate and underlap. Particularly, the optimized Ion in n-type (p-type) device can reach up to 2423 (4277) and 1988 (920) μA/μm for high-performance and low-power applications, respectively. The large Ion values are in the first class among the LD FETs, which can well satisfy the ITRS requirements. We also find that the 7-9-7-AGNR FET can have ultralow subthreshold swing below 60mV/dev, ultrashort delay time (<0.01 ps), and very small power-delay product (<0.01 fJ/μm). Our results show that the 7-9-7-AGNR based FETs have great potential applications in the high-speed and low-power consumption chips.

cond-mat.mes-hall↗

arXiv2023

One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer

Recognizing characters from low-resolution (LR) text images poses a significant challenge due to the information deficiency as well as the noise and blur in low-quality images. Current solutions for low-resolution text recognition (LTR) typically rely on a two-stage pipeline that involves super-resolution as the first stage followed by the second-stage recognition. Although this pipeline is straightforward and intuitive, it has to use an additional super-resolution network, which causes inefficiencies during training and testing. Moreover, the recognition accuracy of the second stage heavily depends on the reconstruction quality of the first stage, causing ineffectiveness. In this work, we attempt to address these challenges from a novel perspective: adapting the recognizer to low-resolution inputs by transferring the knowledge from the high-resolution. Guided by this idea, we propose an efficient and effective knowledge distillation framework to achieve multi-level knowledge transfer. Specifically, the visual focus loss is proposed to extract the character position knowledge with resolution gap reduction and character region focus, the semantic contrastive loss is employed to exploit the contextual semantic knowledge with contrastive learning, and the soft logits loss facilitates both local word-level and global sequence-level learning from the soft teacher label. Extensive experiments show that the proposed one-stage pipeline significantly outperforms super-resolution based two-stage frameworks in terms of effectiveness and efficiency, accompanied by favorable robustness. Code is available at https://github.com/csguoh/KD-LTR.

cs.CV↗

arXiv2023

Towards Robust Scene Text Image Super-resolution via Explicit Location Enhancement

Scene text image super-resolution (STISR), aiming to improve image quality while boosting downstream scene text recognition accuracy, has recently achieved great success. However, most existing methods treat the foreground (character regions) and background (non-character regions) equally in the forward process, and neglect the disturbance from the complex background, thus limiting the performance. To address these issues, in this paper, we propose a novel method LEMMA that explicitly models character regions to produce high-level text-specific guidance for super-resolution. To model the location of characters effectively, we propose the location enhancement module to extract character region features based on the attention map sequence. Besides, we propose the multi-modal alignment module to perform bidirectional visual-semantic alignment to generate high-quality prior guidance, which is then incorporated into the super-resolution branch in an adaptive manner using the proposed adaptive fusion module. Experiments on TextZoom and four scene text recognition benchmarks demonstrate the superiority of our method over other state-of-the-art methods. Code is available at https://github.com/csguoh/LEMMA.

cs.CV↗

arXiv2022

MGTR: End-to-End Mutual Gaze Detection with Transformer

People's looking at each other or mutual gaze is ubiquitous in our daily interactions, and detecting mutual gaze is of great significance for understanding human social scenes. Current mutual gaze detection methods focus on two-stage methods, whose inference speed is limited by the two-stage pipeline and the performance in the second stage is affected by the first one. In this paper, we propose a novel one-stage mutual gaze detection framework called Mutual Gaze TRansformer or MGTR to perform mutual gaze detection in an end-to-end manner. By designing mutual gaze instance triples, MGTR can detect each human head bounding box and simultaneously infer mutual gaze relationship based on global image information, which streamlines the whole process with simplicity. Experimental results on two mutual gaze datasets show that our method is able to accelerate mutual gaze detection process without losing performance. Ablation study shows that different components of MGTR can capture different levels of semantic information in images. Code is available at https://github.com/Gmbition/MGTR

cs.CV↗

arXiv2020

Peek Inside the Closed World: Evaluating Autoencoder-Based Detection of DDoS to Cloud

Machine-learning-based anomaly detection (ML-based AD) has been successful at detecting DDoS events in the lab. However published evaluations of ML-based AD have used only limited data and provided minimal insight into why it works. To address limited evaluation against real-world data, we apply autoencoder, an existing ML-AD model, to 57 DDoS attack events captured at 5 cloud IPs from a major cloud provider. We show that our models detect nearly all malicious flows for 2 of the 4 cloud IPs under attack (at least 99.99%) and detect most malicious flows (94.75% and 91.37%) for the remaining 2 IPs. Our models also maintain near-zero false positives on benign flows to all 5 IPs. Our primary contribution is to improve our understanding for why ML-based AD works on some malicious flows but not others. We interpret our detection results with feature attribution and counterfactual explanation. We show that our models are better at detecting malicious flows with anomalies on allow-listed features (those with only a few benign values) than flows with anomalies on deny-listed features (those with mostly benign values) because our models are more likely to learn correct normality for allow-listed features. We then show that our models are better at detecting malicious flows with anomalies on unordered features (that have no ordering among their values) than flows with anomalies on ordered features because even with incomplete normality, our models could still detect anomalies on unordered feature with high recall. Lastly, we summarize the implications of what we learn on applying autoencoder-based AD in production: training with noisy real-world data is possible, autoencoder can reliably detect real-world anomalies on well-represented unordered features and combinations of autoencoder-based AD and heuristic-based filters can help both.

cs.NI↗