9 papers
MV2GF: Multi-view Pedestrian Detection with a Visual Geometric Foundation Model
Taiga Yamane, Satoshi Suzuki, Ryo Masumura +4
Multi-View Pedestrian Detection (MVPD) aims to detect pedestrians in the form of a bird's eye view map from multi-view images. Recent MVPD methods adopt a unified framework that pr…
Difference Vector Equalization for Robust Fine-tuning of Vision-Language Models
Satoshi Suzuki, Shin'ya Yamaguchi, Shoichiro Takeda +7
Contrastive pre-trained vision-language models, such as CLIP, demonstrate strong generalization abilities in zero-shot classification by leveraging embeddings extracted from image…
MVAFormer: RGB-based Multi-View Spatio-Temporal Action Recognition with Transformer
Taiga Yamane, Satoshi Suzuki, Ryo Masumura +1
Multi-view action recognition aims to recognize human actions using multiple camera views and deals with occlusion caused by obstacles or crowds. In this task, cooperation among vi…
Joint Modeling of Big Five and HEXACO for Multimodal Apparent Personality-trait Recognition
Ryo Masumura, Shota Orihashi, Mana Ihori +6
This paper proposes a joint modeling method of the Big Five, which has long been studied, and HEXACO, which has recently attracted attention in psychology, for automatically recogn…
Few-shot Personalization via In-Context Learning for Speech Emotion Recognition based on Speech-Language Model
Mana Ihori, Taiga Yamane, Naotaka Kawata +5
This paper proposes a personalization method for speech emotion recognition (SER) through in-context learning (ICL). Since the expression of emotions varies from person to person,…
MVTrajecter: Multi-View Pedestrian Tracking with Trajectory Motion Cost and Trajectory Appearance Cost
Taiga Yamane, Ryo Masumura, Satoshi Suzuki +1
Multi-View Pedestrian Tracking (MVPT) aims to track pedestrians in the form of a bird's eye view occupancy map from multi-view videos. End-to-end methods that detect and associate…
MSMVD: Exploiting Multi-scale Image Features via Multi-scale BEV Features for Multi-view Pedestrian Detection
Taiga Yamane, Satoshi Suzuki, Ryo Masumura +5
Multi-View Pedestrian Detection (MVPD) aims to detect pedestrians in the form of a bird's eye view (BEV) from multi-view images. In MVPD, end-to-end trainable deep learning methods…
ToMATO: Verbalizing the Mental States of Role-Playing LLMs for Benchmarking Theory of Mind
Kazutoshi Shinoda, Nobukatsu Hojo, Kyosuke Nishida +5
Existing Theory of Mind (ToM) benchmarks diverge from real-world scenarios in three aspects: 1) they assess a limited range of mental states such as beliefs, 2) false beliefs are n…
Boosting Hybrid Autoregressive Transducer-based ASR with Internal Acoustic Model Training and Dual Blank Thresholding
Takafumi Moriya, Takanori Ashihara, Masato Mimura +4
A hybrid autoregressive transducer (HAT) is a variant of neural transducer that models blank and non-blank posterior distributions separately. In this paper, we propose a novel int…