paper-with-me

Papers

MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking

2021-07-22 · Xiao Wang, Xiujun Shu, Shiliang Zhang, Bo Jiang, YaoWei Wang, Yonghong Tian, Feng Wu

Many RGB-T trackers attempt to attain robust feature representation by utilizing an adaptive weighting scheme (or attention mechanism). Different from these works, we propose a new dynamic modality-aware filter generation module (named MFGNet) to boost the message communication between visible and thermal data by adaptively adjusting the convolutional kernels for various input images in practical tracking. Given the image pairs as input, we first encode their features with the backbone network. Then, we concatenate these feature maps and generate dynamic modality-aware filters with two independent networks. The visible and thermal filters will be used to conduct a dynamic convolutional operation on their corresponding input feature maps respectively. Inspired by residual connection, both the generated visible and thermal feature maps will be summarized with input feature maps. The augmented feature maps will be fed into the RoI align module to generate instance-level features for subsequent classification. To address issues caused by heavy occlusion, fast motion and out-of-view, we propose to conduct a joint local and global search by exploiting a new direction-aware target driven attention mechanism. The spatial and temporal recurrent neural network is used to capture the direction-aware context for accurate global attention prediction. Extensive experiments on three large-scale RGB-T tracking benchmark datasets validated the effectiveness of our proposed algorithm. The source code of this paper is available at \textcolor{magenta}{\url{https://github.com/wangxiao5791509/MFG_RGBT_Tracking_PyTorch}}.

📄 PDF Abstract BibTeX arXiv:2107.10433

Code (2)

wangxiao5791509/MFG_RGBT_Tracking_PyTorch 공식 구현 pytorch
wangxiao5791509/DFG_RGBT_Tracking_PyTorch pytorch

Tasks

Rgb-T Tracking

Similar Papers 제목 키워드 기반

Rebalanced Multimodal Learning with Data-aware Unimodal Sampling

2025-03-05 · QingYuan Jiang, Zhouyang Chi, Xiao Ma, Qirong Mao 외

To address the modality learning degeneration caused by modality imbalance, existing multimodal learning~(MML) approaches primarily attempt to balance the optimization process of each modality from the perspective of mod…

Reinforcement Learning (RL)

Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity

2026-05-12 · Sirui Zhang, Haonan Wang, Xunkai Li, Zekai Chen 외 arxiv

Recently, multimodal graph learning (MGL) has garnered significant attention for integrating diverse modality information and structured context to support various network applications. However, real-world graphs are oft…

Graph Learning

Dynamic Gated Cross-Modal Fusion with Sarcastic-aware Contrastive Regularization for Multimodal Sarcasm Detection

2026-08-20 · Hao Guo, Subin Huang, Junjie Chen, Zhifa Geng 외 arxiv

Multimodal sarcasm detection aims to identify sarcastic intent from multimodal content, where inconsistencies between literal meaning and contextual cues often signal irony. This task has attracted increasing research at…

Sarcasm Detection

Unifying Value Alignment and Assignment in Cross-Domain Offline Reinforcement Learning with Heterogeneous Datasets

2026-05-24 · Zhongjian Qiao, Jiafei Lyu, Chenjia Bai, Peisong Wang 외 arxiv

Cross-domain offline reinforcement learning (RL) aims to learn a policy in the target domain with a limited target domain dataset and a source domain dataset that exhibits a dynamics shift. Training directly on the origi…

Representation LearningReinforcement LearningOffline RL

TimeMM: Time-as-Operator Spectral Filtering for Dynamic Multimodal Recommendation

2026-04-29 · Wei Yang, Rui Zhong, Zihan Lin, Xiaodan Wang 외 arxiv

Multimodal recommendation improves user modeling by integrating collaborative signals with heterogeneous item content. In real applications, user interests evolve over time and exhibit nonstationary dynamics, where diffe…

Multimodal Recommendation