科研成果 by Type: Conference Paper

2024
Y. Liu, Y. Ma, N. Shang, T. Zhao, P. Chen, M. Wu, J. Ru, T. Jia, L. Ye, Z. Wang, et al. A 22nm 0.26nW/synapse spike-driven spiking neural network processing unit using time-step-first dataflow and sparsity-adaptive in-memory computing, in IEEE International Solid-State Circuits Conference (ISSCC).; 2024.
Loscalzo E, Cochet M, Zuckerman J, Zaliasl S, Lekas M, Cahill S, Jia T, Swaminathan K, dos Santos MC, Giri D, et al. A 400-ns-Settling-Time Hybrid Dynamic Voltage Frequency Scaling Architecture and Its Application in a 22-Core Network-on-Chip SoC in 12nm FinFET Technology, in IEEE Symposium on VLSI Technology & Circuits (VLSI).; 2024.
Liu C, Yu X, Wang D, Jiang T. ACLNet: A Deep Learning Model for ACL Rupture Classification Combined with Bone Morphology, in The 27th International Conference on Medical Image Computing and Computer Assisted Intervention,MICCAI 2024, October 6-10.Vol 15005. Marrakesh, Morocco: Springer; 2024:57–67. 访问链接Abstract
Magnetic Resonance Imaging (MRI) is widely used in diagnosing anterior cruciate ligament (ACL) injuries due to its ability to provide detailed image data. However, existing deep learning approaches often overlook additional factors beyond the image itself. In this study, we aim to bridge this gap by exploring the relationship between ACL rupture and the bone morphology of the femur and tibia. Leveraging extensive clinical experience, we acknowledge the significance of this morphological data, which is not readily observed manually. To effectively incorporate this vital information, we introduce ACLNet, a novel model that combines the convolutional representation of MRI images with the transformer representation of bone morphological point clouds. This integration significantly enhances ACL injury predictions by leveraging both imaging and geometric data. Our methodology demonstrated an enhancement in diagnostic precision on the in-house dataset compared to image-only methods, elevating the accuracy from 87.59% to 92.57%. This strategy of utilizing implicitly relevant information to enhance performance holds promise for a variety of medical-related tasks.
Yu B, Liang J, Wang Z, Fan B, Subpa-asa A, Shi B, Sato I. Active Hyperspectral Imaging Using an Event Camera, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).; 2024.Abstract
Hyperspectral imaging plays a critical role in numerous scientific and industrial fields. Conventional hyperspectral imaging systems often struggle with the trade-off between spectral and temporal resolution, particularly in dynamic environments. In ours work, we present an innovative event-based active hyperspectral imaging system designed for real-time performance in dynamic scenes. By integrating a diffraction grating and rotating mirror with an event-based camera, the proposed system captures high-fidelity spectral information at a microsecond temporal resolution, leveraging the event camera's unique capability to detect instantaneous changes in brightness rather than absolute intensity. The proposed system trade-off between conventional frame-based systems by reducing the bandwidth and computational load and mosaic-based system by remaining the original sensor spatial resolution. It records only meaningful changes in brightness, achieving high temporal and spectral resolution with minimal latency and is practical for real-time applications in complex dynamic conditions.
Jing Y, Wu M, Zhou J, Sun Y, Ma Y, HUANG R, Ye L, Jia T. AIG-CIM: A Scalable Chiplet Module with Tri-Gear Heterogeneous Compute-in-Memory for Diffusion Acceleration, in Design Automation Conference (DAC).; 2024.
Wu C-Y. Aquila's Roads: Connecting Paphlagonian Spaces., in 18th International Conference of the Taiwan Association of Classical, Medieval and Renaissance Studies, November 1-2, 2024. National Taiwan University, Taipei, China.; 2024.
Qian Y, Qu T, Tang W, Chen S, Shen W, Guo X, Chai H. Automotive acoustic channel equalization method using convex optimization in modal domain, in the AES 156th Convention. Madrid, Spain; 2024:11696.Abstract
Automotive audio systems often face sub-optimal sound quality due to the intricate acoustic properties of car cabins. Acoustic channel equalization methods are generally employed to improve sound reproduction quality in such environments. In this paper, we propose an acoustic channel equalization method using convex optimization in the modal domain. The modal domain representation is used to model the whole sound field to be equalized. Besides integrating it into the convex formulation of the acoustic channel reshaping problem, to further control the prering artifacts, the temporal window function modified according to the backward masking effect of the human auditory system is used during equalizer design. Objective and subjective experiments in a real automotive cabin proved that the proposed method enhances spatial robustness and avoids the audible prering artifacts.
Liu Z, Li Z, Jiang T. BLADE: Box-Level Supervised Amodal Segmentation through Directed Expansion, in The 38th AAAI Conference on Artificial Intelligence, AAAI 2024, Feb. 20-27. Vancouver, Canada: AAAI Press; 2024:3846–3854. 访问链接
Cochet M, Swaminathan K, Loscalzo EJ, Zuckerman J, dos Santos MC, Giri D, Buyuktosunoglu A, Jia T, Brooks D, Wei G-Y, et al. BlitzCoin: Fully Decentralized Hardware Power Management for Accelerator-Rich SoCs, in International Symposium on Computer Architecture (ISCA).; 2024.
Zhong Y, Wu X, Zhang L, Yang C, Jiang T. Causal-IQA: Towards the Generalization of Image Quality Assessment Based on Causal Inference, in The 41st International Conference on Machine Learning, ICML 2024, July 21-27. Vienna, Austria; 2024. 访问链接
Li W, Tang Z, Zhang P, Wang J. Collaborative Data Behaviors in Digital Humanities Research Teams, in ACM IEEE Joint Conference on Digital Libraries (JCDL 24). Hongkong, China; 2024.
Yang L, Xu C, Ma Xinyu, Gao Xin, Li Ruiqing, Yasha W. Combating Label Sparsity in Short Text Topic Modeling via Nearest Neighbor Augmentation, in In Findings of The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024).; 2024.
Xu X, Wang B, Yan Y, Zhu H, Zhang Z, Wu X, Chen J*. ConvConcatNet: a deep convolutional neural network to reconstruct mel spectrogram from the EEG, in arXiv; 2024. 访问链接
Hagag A, Gomaa A, Kornek D, Maier A, Fietkau R, Bert C, Huang Y, Putz F. Deep Learning for Cancer Prognosis Prediction Using Portrait Photos by StyleGAN Embedding, in International Conference on Medical Image Computing and Computer-Assisted Intervention.; 2024:early–acceptance.
Liu Y, Yang C, Li D, Ding J, Jiang T. Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization, in IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, June 16-22. Seattle, WA, USA: IEEE; 2024:25554–25563. 访问链接
Xu X, Wang B, Yan Y, Wu X, Chen J*. A DenseNet-Based Method for Decoding Auditory Spatial Attention with EEG, in ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).; 2024:1946–1950. 访问链接
Salminen J, Liu C, Pian W, Chi J, Häyhänen E, Jansen BJ. Deus ex machina and personas from large language models: investigating the composition of AI-generated persona descriptions, in Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems.; 2024:1–20.
Wang Q, Wang Y, Wang Y, Ying X. Dissecting the Failure of Invariant Learning on Graphs, in Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024.; 2024. 访问链接
Gao S, Wu X, Qu T. DOA-Informed Self-Supervised Learning Method for SoundSource Enhancement, in the AES 156th Convention. Madrid, Spain; 2024:10683.Abstract
The multiple-channel[1] sound source enhancement methods have made a great progress in recent years, especially when combined with the learning-based algorithms. However, the performance of these techniques is limited by the completeness of the training dataset, which may degrade in mismatched environments. In this paper, we propose a reconstruction Model based Self-supervised Learning (RMSL) method for sound source enhancement. A reconstruction module is used to integrate the estimated target signal and noise components to regenerate the multi-channel mixed signals, and it is connected with a separating model to form a closed loop.In this case, the optimization of the separation model can be achieved by continuously iterating the separation-reconstruction process. We use the separation error, the reconstruction error, and the signal-noise independence error as lossfunctions in the self-supervised learning process. This method is applied to the state-of-the-art sound source separation model (ADL-MVDR) and evaluated under different scenarios. Experimental results demonstrate that the proposed method can improve the performance of ADL-MVDR algorithm under different number of sound sources, bringing about 0.5 dB to 1 dB Si-SNR gain, while maintaining good clarity and intelligibility in practical application.
Gao X, Lin Y, Li R, Wang Y, Chu X, Ma X, Yu H. Enhancing Topic Interpretability for Neural Topic Modeling Through Topic-Wise Contrastive Learning, in 2024 IEEE 40th International Conference on Data Engineering (ICDE 2024).; 2024.

Pages