大模型推理能力 - arXivDaily 专题

2307.11192 2023-07-24 cs.RO 50%

Adapting to Human Preferences to Lead or Follow in Human-Robot Collaboration: A System Evaluation

Ali Noormohammadi-Asl, Ali Ayub, Stephen L. Smith, Kerstin Dautenhahn

专题命中推理评测：planning(abstract)

2307.05096 2023-07-12 cs.SD eess.AS 50%

The smarty4covid dataset and knowledge base: a framework enabling interpretable analysis of audio signals

Konstantia Zarkogianni, Edmund Dervakos, George Filandrianos, Theofanis Ganitidis, Vasiliki Gkatzou, Aikaterini Sakagianni, Raghu Raghavendra, C. L. Max Nikias, Giorgos Stamou, Konstantina S. Nikita

专题命中推理评测：reasoning(abstract)

Comments Submitted for publication in Nature Scientific Data

2306.03932 2023-06-08 cs.CV 50%

Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!

Zaid Khan, Vijay Kumar BG, Samuel Schulter, Xiang Yu, Yun Fu, Manmohan Chandraker

专题命中推理评测：reasoning(abstract)

Comments CVPR 2023

2211.05707 2023-04-19 physics.med-ph physics.hist-ph 50%

Critique of optical coherence tomography in epistemological metrology

Yoshiaki Yasuno

专题命中推理评测：reasoning(abstract)

2304.02556 2023-04-06 cs.CV 50%

Detecting and Grounding Multi-Modal Media Manipulation

Rui Shao, Tianxing Wu, Ziwei Liu

专题命中推理评测：reasoning(abstract)

Comments CVPR 2023. Project page: https://rshaojimmy.github.io/Projects/MultiModal-DeepFake Code: https://github.com/rshaojimmy/MultiModal-DeepFake

2208.03543 2023-03-24 cs.CV 50%

MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer

Chaoqiang Zhao, Youmin Zhang, Matteo Poggi, Fabio Tosi, Xianda Guo, Zheng Zhu, Guan Huang, Yang Tang, Stefano Mattoccia

专题命中推理评测：reasoning(abstract)

Comments Accepted by 3DV 2022

2303.09192 2023-03-17 cs.RO 50%

Metric-Free Exploration for Topological Mapping by Task and Motion Imitation in Feature Space

Yuhang He, Irving Fang, Yiming Li, Rushi Bhavesh Shah, Chen Feng

专题命中推理评测：planning(abstract)

2303.06330 2023-03-14 cs.CV 50%

PRSNet: A Masked Self-Supervised Learning Pedestrian Re-Identification Method

Zhijie Xiao, Zhicheng Dong, Hao Xiang

专题命中推理评测：reasoning(abstract)

2302.10817 2023-02-22 cs.RO cs.MA 50%

Inferring Implicit Trait Preferences for Task Allocation in Heterogeneous Teams

Vivek Mallampati, Harish Ravichandar

专题命中推理评测：reasoning(abstract)

Comments 8 pages, 5 figures, to be published as extended abstract in AAMAS 2023

2302.00673 2023-02-02 cs.CV cs.HC 50%

ADAPT: Action-aware Driving Caption Transformer

Bu Jin, Xinyu Liu, Yupeng Zheng, Pengfei Li, Hao Zhao, Tong Zhang, Yuhang Zheng, Guyue Zhou, Jingjing Liu

专题命中推理评测：reasoning(abstract)

Comments Accepted to ICRA2023. Code: https://github.com/jxbbb/ADAPT

2301.12048 2023-01-31 cs.CV eess.IV 50%

Making Reconstruction-based Method Great Again for Video Anomaly Detection

Yizhou Wang, Can Qin, Yue Bai, Yi Xu, Xu Ma, Yun Fu

专题命中推理评测：reasoning(abstract)

Comments Accepted by ICDM 2022

2203.08912 2022-11-15 cs.SE 50%

The Best of Both Worlds: Combining Learned Embeddings with Engineered Features for Accurate Prediction of Correct Patches

Haoye Tian, Kui Liu, Yinghua Li, Abdoul Kader Kaboré, Anil Koyuncu, Andrew Habib, Li Li, Junhao Wen, Jacques Klein, Tegawendé F. Bissyandé

专题命中推理评测：reasoning(abstract)

Comments arXiv admin note: substantial text overlap with arXiv:2008.02944

2210.17302 2022-11-08 cs.RO cs.SY eess.SY 50%

Design, Field Evaluation, and Traffic Analysis of a Competitive Autonomous Driving Model in a Congested Environment

Daegyu Lee, Hyunki Seong, Seungil Han, Gyuree Kang, D. Hyunchul Shim, Yoonjin Yoon

专题命中推理评测：planning(abstract)

2210.10828 2022-10-21 cs.CV 50%

Grounded Video Situation Recognition

Zeeshan Khan, C. V. Jawahar, Makarand Tapaswi

专题命中推理评测：reasoning(abstract)

Comments Accepted to NeurIPS 2022. Project Page: https://zeeshank95.github.io/grvidsitu

2203.07682 2022-10-21 cs.CV 50%

Enriched CNN-Transformer Feature Aggregation Networks for Super-Resolution

Jinsu Yoo, Taehoon Kim, Sihaeng Lee, Seung Hwan Kim, Honglak Lee, Tae Hyun Kim

专题命中推理评测：reasoning(abstract)

Comments WACV 2023

2210.00828 2022-10-04 cs.CV 50%

Mastering Spatial Graph Prediction of Road Networks

Sotiris Anagnostidis, Aurelien Lucchi, Thomas Hofmann

专题命中推理评测：reasoning(abstract)

2109.05014 2022-09-15 cs.CV 50%

An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA

Zhengyuan Yang, Zhe Gan, Jianfeng Wang, Xiaowei Hu, Yumao Lu, Zicheng Liu, Lijuan Wang

专题命中推理评测：reasoning(abstract)

Comments AAAI 2022 (Oral Presentation)

2208.07256 2022-08-16 cs.RO cs.CV 50%

Multi-modal Transformer Path Prediction for Autonomous Vehicle

Chia Hong Tseng, Jie Zhang, Min-Te Sun, Kazuya Sakai, Wei-Shinn Ku

专题命中推理评测：reasoning(abstract)

Comments 9 pages, 12 figures, and 5 tables

2208.01897 2022-08-04 cs.CV 50%

Combined CNN Transformer Encoder for Enhanced Fine-grained Human Action Recognition

Mei Chee Leong, Haosong Zhang, Hui Li Tan, Liyuan Li, Joo Hwee Lim

专题命中推理评测：reasoning(abstract)

Comments The Ninth Workshop on Fine-Grained Visual Categorization (FGVC9) @ CVPR2022

2207.14012 2022-07-29 cs.CV 50%

Video Mask Transfiner for High-Quality Video Instance Segmentation

Lei Ke, Henghui Ding, Martin Danelljan, Yu-Wing Tai, Chi-Keung Tang, Fisher Yu

专题命中推理评测：self-correction(abstract)

Comments ECCV 2022; Project page: https://www.vis.xyz/pub/vmt; Dataset page: https://www.vis.xyz/data/hqvis

2207.07381 2022-07-18 cs.CV 50%

A Dual-Masked Auto-Encoder for Robust Motion Capture with Spatial-Temporal Skeletal Token Completion

Junkun Jiang, Jie Chen, Yike Guo

专题命中推理评测：reasoning(abstract)

2204.04655 2022-07-12 cs.CV 50%

Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation

Xiangtai Li, Shilin Xu, Yibo Yang, Guangliang Cheng, Yunhai Tong, Dacheng Tao

专题命中推理评测：reasoning(abstract)

Comments ECCV-2022

2206.09907 2022-06-28 cs.CV 50%

ORFD: A Dataset and Benchmark for Off-Road Freespace Detection

Chen Min, Weizhong Jiang, Dawei Zhao, Jiaolong Xu, Liang Xiao, Yiming Nie, Bin Dai

专题命中推理评测：planning(abstract)

Comments Accepted by ICRA2022

2206.05712 2022-06-14 cs.CV 50%

Graph-based Spatial Transformer with Memory Replay for Multi-future Pedestrian Trajectory Prediction

Lihuan Li, Maurice Pagnucco, Yang Song

专题命中推理评测：planning(abstract)

Comments This paper has been accepted by CVPR 2022. Reference: Li, L., Pagnucco, M. and Song, Y., 2022. Graph-Based Spatial Transformer With Memory Replay for Multi-Future Pedestrian Trajectory Prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 2231-2241)

2203.11192 2022-03-22 cs.CV 50%

Transforming Model Prediction for Tracking

Christoph Mayer, Martin Danelljan, Goutam Bhat, Matthieu Paul, Danda Pani Paudel, Fisher Yu, Luc Van Gool

专题命中推理评测：reasoning(abstract)

Comments Accepted at CVPR 2022. The code and trained models are available at https://github.com/visionml/pytracking

2201.00802 2022-01-04 physics.chem-ph 50%

Learning Small Molecule Energies and Interatomic Forces with an Equivariant Transformer on the ANI-1x Dataset

Bryce Hedelius, Fabian B. Fuchs, Dennis Della Corte

专题命中推理评测：reasoning(abstract)

Comments 4 pages, 2 figures, accepted to the poster session of ELLIS Machine Learning for Molecule Discovery Workshop 2021

Journal ref https://moleculediscovery.github.io/workshop2021/

2101.03531 2021-12-01 cs.CV 50%

Channel Boosting Feature Ensemble for Radar-based Object Detection

Shoaib Azam, Farzeen Munir, Moongu Jeon

专题命中推理评测：planning(abstract)

2006.00753 2021-11-29 cs.CV 50%

Structured Multimodal Attentions for TextVQA

Chenyu Gao, Qi Zhu, Peng Wang, Hui Li, Yuliang Liu, Anton van den Hengel, Qi Wu

专题命中推理评测：reasoning(abstract)

Comments winner of TextVQA Challenge 2020, Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence

2010.11585 2021-11-16 cs.MA cs.SY eess.SY 50%

A simulation-based evaluation of a Cargo-Hitching service for E-commerce using mobility-on-demand vehicles

Andre Alho, Takanori Sakai, Simon Oh, Cheng Cheng, Ravi Seshadri, Wen Han Chong, Yusuke Hara, Julia Caravias, Lynette Cheah, Moshe Ben-Akiva

专题命中推理评测：planning(abstract)

Comments 19 pages, 4 tables, 7 figures. Submitted to Transportation (Springer)

Journal ref Future Transp. 2021, 1, 639-656

2110.09481 2021-10-19 cs.CV cs.MA cs.RO 50%

MTP: Multi-Hypothesis Tracking and Prediction for Reduced Error Propagation

Xinshuo Weng, Boris Ivanovic, Marco Pavone

专题命中推理评测：planning(abstract)

Comments Project page: https://www.xinshuoweng.com/projects/MTP

1. 推理评测 10577 篇

Adapting to Human Preferences to Lead or Follow in Human-Robot Collaboration: A System Evaluation

The smarty4covid dataset and knowledge base: a framework enabling interpretable analysis of audio signals

Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!

Critique of optical coherence tomography in epistemological metrology

Detecting and Grounding Multi-Modal Media Manipulation

MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer

Metric-Free Exploration for Topological Mapping by Task and Motion Imitation in Feature Space

PRSNet: A Masked Self-Supervised Learning Pedestrian Re-Identification Method

Inferring Implicit Trait Preferences for Task Allocation in Heterogeneous Teams

ADAPT: Action-aware Driving Caption Transformer

Making Reconstruction-based Method Great Again for Video Anomaly Detection

The Best of Both Worlds: Combining Learned Embeddings with Engineered Features for Accurate Prediction of Correct Patches

Design, Field Evaluation, and Traffic Analysis of a Competitive Autonomous Driving Model in a Congested Environment

Grounded Video Situation Recognition

Enriched CNN-Transformer Feature Aggregation Networks for Super-Resolution

Mastering Spatial Graph Prediction of Road Networks

An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA

Multi-modal Transformer Path Prediction for Autonomous Vehicle

Combined CNN Transformer Encoder for Enhanced Fine-grained Human Action Recognition

Video Mask Transfiner for High-Quality Video Instance Segmentation

A Dual-Masked Auto-Encoder for Robust Motion Capture with Spatial-Temporal Skeletal Token Completion

Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation

ORFD: A Dataset and Benchmark for Off-Road Freespace Detection

Graph-based Spatial Transformer with Memory Replay for Multi-future Pedestrian Trajectory Prediction

Transforming Model Prediction for Tracking

Learning Small Molecule Energies and Interatomic Forces with an Equivariant Transformer on the ANI-1x Dataset

Channel Boosting Feature Ensemble for Radar-based Object Detection

Structured Multimodal Attentions for TextVQA

A simulation-based evaluation of a Cargo-Hitching service for E-commerce using mobility-on-demand vehicles

MTP: Multi-Hypothesis Tracking and Prediction for Reduced Error Propagation