Search Results - "Lan, Zhenzhong"

Beyond Gaussian Pyramid: Multi-skip Feature Stacking for action recognition by Zhenzhong Lan, Ming Lin, Xuanchong Li, Hauptmann, Alexander G., Raj, Bhiksha

“…Most state-of-the-art action feature extractors involve differential operators, which act as highpass filters and tend to attenuate low frequency action…”
Get full text

Beyond Binary Classification: A Fine-Grained Safety Dataset for Large Language Models by Yu, Jia, Li, Long, Lan, Zhenzhong

“…Large Language Models (LLMs) excel in interactive chat scenarios due to their advanced conversational abilities. However, their training process invariably…”
Get full text

Deep Local Video Feature for Action Recognition by Zhenzhong Lan, Yi Zhu, Hauptmann, Alexander G., Newsam, Shawn

“…We investigate the problem of representing an entire video using CNN features for human action recognition. End-to-end learning of CNN/RNNs is currently not…”
Get full text

Deep Graph Convolutional Network for Small-Molecule Retention Time Prediction by Kang, Qiyue, Fang, Pengfei, Zhang, Shuai, Qiu, Huachuan, Lan, Zhenzhong

“…The retention time (RT) is a crucial source of data for liquid chromatography-mass spectrometry (LCMS). A model that can accurately predict the RT for each…”
Get full text

Poincaré Kernels for Hyperbolic Representations by Fang, Pengfei, Harandi, Mehrtash, Lan, Zhenzhong, Petersson, Lars

“…Embedding data in hyperbolic spaces has proven beneficial for many advanced machine learning applications. However, working in hyperbolic spaces is not without…”
Get full text

Beyond a strong baseline: cross-modality contrastive learning for visible-infrared person re-identification by Fang, Pengfei, Zhang, Yukang, Lan, Zhenzhong

“…Cross-modality pedestrian image matching, which entails the matching of visible and infrared images, is a vital area in person re-identification (reID) due to…”
Get full text

Coking and gas products behavior of supercritical n-decane over NiO nanoparticle/nanosheets modified HZSM-5 by Long, Lin, Zhou, Weixing, Qiu, Yunfeng, Lan, Zhenzhong

“…Endothermic hydrocarbon fuel of active thermal protection has great potential in cooling system. The bottlenecks for the practical application are the…”
Get full text

Air-to-Air Visual Detection of Micro-UAVs: An Experimental Evaluation of Deep Learning by Zheng, Ye, Chen, Zhang, Lv, Dailin, Li, Zhixing, Lan, Zhenzhong, Zhao, Shiyu

“…This letter studies the problem of air-to-air visual detection of micro unmanned aerial vehicles (UAVs) by monocular cameras. This problem is important for…”
Get full text

Offline prompt polishing for low quality instructions by Yu, Jia, Zhou, Zhanchao, Li, Long, Li, Ling, Yan, Yuming, Xu, Renjun, Lan, Zhenzhong

“…Instruction-tuning is an effective avenue for making large language models (LLMs) better at following real users’ instructions. However, it is challenging in…”
Get full text

Co3O4 Nanosheet Wrapped Commercial HZSM‑5 for Promoting Catalytic Cracking of n‑Decane and Anticoking Activities by Long, Lin, Lan, Zhenzhong, Han, Zhixiong, Qiu, Yunfeng, Zhou, Weixing

“…Endothermic hydrocarbon fuel has many advantages as a cooling medium in hypersonic aircraft; however substantial application has been greatly hindered due to…”
Get full text

Eyes on nature: Embedded vision cameras for terrestrial biodiversity monitoring by Darras, Kevin F. A., Balle, Marcel, Xu, Wenxiu, Yan, Yang, Zakka, Vincent G., Toledo‐Hernández, Manuel, Sheng, Dong, Lin, Wei, Zhang, Boyu, Lan, Zhenzhong, Fupeng, Li, Wanger, Thomas C.

“…Abstract We need comprehensive information to manage and protect biodiversity in the face of global environmental challenges, and artificial intelligence is…”
Get full text

Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions by Qiu, Huachuan, Lan, Zhenzhong

“…Virtual counselors powered by large language models (LLMs) aim to create interactive support systems that effectively assist clients struggling with mental…”
Get full text

Co 3 O 4 Nanosheet Wrapped Commercial HZSM-5 for Promoting Catalytic Cracking of n -Decane and Anticoking Activities by Long, Lin, Lan, Zhenzhong, Han, Zhixiong, Qiu, Yunfeng, Zhou, Weixing

Get full text

Transferred Feature Selection by Wei Bi, Yuan Shi, Zhenzhong Lan

“…Traditional feature selection algorithms require a large number of labeled training instances to find out the most informative subset of features. However, in…”
Get full text

S-SimCSE: Sampled Sub-networks for Contrastive Learning of Sentence Embedding by Zhang, Junlei, lan, Zhenzhong

“…Contrastive learning has been studied for improving the performance of learning sentence embeddings. The current state-of-the-art method is the SimCSE, which…”
Get full text

PsyGUARD: An Automated System for Suicide Detection and Risk Assessment in Psychological Counseling by Qiu, Huachuan, Ma, Lizhi, Lan, Zhenzhong

“…As awareness of mental health issues grows, online counseling support services are becoming increasingly prevalent worldwide. Detecting whether users express…”
Get full text

E-LAMP: integration of innovative ideas for multimedia event detection by Tong, Wei, Yang, Yi, Jiang, Lu, Yu, Shoou-I, Lan, ZhenZhong, Ma, Zhigang, Sze, Waito, Younessian, Ehsan, Hauptmann, Alexander G.

“…Detecting multimedia events in web videos is an emerging hot research area in the fields of multimedia and computer vision. In this paper, we introduce the…”
Get full text

Extending Semi-supervised Learning Methods for Inductive Transfer Learning by Yuan Shi, Zhenzhong Lan, Wei Liu, Wei Bi

“…Inductive transfer learning and semi-supervised learning are two different branches of machine learning. The former tries to reuse knowledge in labeled…”
Get full text

Contrastive Learning of Sentence Embeddings from Scratch by Zhang, Junlei, Lan, Zhenzhong, He, Junxian

“…Contrastive learning has been the dominant approach to train state-of-the-art sentence embeddings. Previous studies have typically learned sentence embeddings…”
Get full text

Value Residual Learning For Alleviating Attention Concentration In Transformers by Zhou, Zhanchao, Wu, Tianyi, Jiang, Zhiyun, Lan, Zhenzhong

“…Transformers can capture long-range dependencies using self-attention, allowing tokens to attend to all others directly. However, stacking multiple attention…”
Get full text