Author name cluster

Jifeng Ning

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

AAAI Conference 2026 Conference Paper

Exploring Modality-Aware Fusion and Decoupled Temporal Propagation for Multi-Modal Object Tracking

Shilei Wang
Pujian Lai
Dong Gao
Jifeng Ning
Gong Cheng

Most existing multi-modal trackers adopt uniform fusion strategies, overlooking the inherent differences between modalities. Moreover, they propagate temporal information through mixed tokens, leading to entangled and less discriminative temporal representations. To address these limitations, we propose MDTrack, a novel framework for modality-aware fusion and decoupled temporal propagation in multi-modal object tracking. Specifically, for modality-aware fusion, we allocate dedicated experts to each modality (Infrared, Event, Depth, and RGB) to process their respective representations. The gating mechanism within the Mixture of Experts (MoE) then dynamically selects the optimal experts based on the input features, enabling adaptive and modality-specific fusion. For decoupled temporal propagation, we introduce two separate State Space Model (SSM) structures to independently store and update the hidden states h of the RGB and X-modal streams, effectively capturing their distinct temporal information. To ensure synergy between the two temporal representations, we incorporate a set of cross-attentions between the input features of the two SSMs, facilitating implicit information exchange. The resulting temporally enriched features are then integrated into the backbone via another set of cross-attention, enhancing MDTrack’s ability to leverage temporal information. Extensive experiments demonstrate the effectiveness of our proposed method. Both MDTrack-S (Modality-Specific Training) and MDTrack-U (Unified-Modality Training) achieve state-of-the-art performance across five multi-modal tracking benchmarks.

PDF Details DOI

EAAI Journal 2026 Journal Article

Precise weed identification and differentiated laser weeding strategies for Salvia miltiorrhiza fields based on an enhanced object detection network

Xianlin Cao
Jinkai Zhang
Kaidong Liu
Xinyu Wu
Yatuan Ma
Jifeng Ning
Shuqin Yang

Effective weed control is crucial for Salvia miltiorrhiza cultivation, yet traditional methods are often inefficient, costly, or polluting. To address this, this study developed a laser weeding robot based on an improved object detection model capable of identifying weeds and implementing targeted strategies. First, a self-propelled laser weeding robot was constructed for Salvia miltiorrhiza fields to meet operational requirements. Second, a real-world field dataset was established for Salvia miltiorrhiza and five weed families. The detection model, optimized from the You Only Look Once (YOLO) architecture, integrates attention-based feature interaction, dynamic spatial attention, and small object feature enhancement modules. These improvements enhanced the features of small objects, improved occluded target localization, and strengthened similar object discrimination. Third, drawing on weed biological characteristics, a multi-level, differentiated laser weeding strategy was developed to precisely target growth points while ensuring crop safety. Finally, the model and strategy were deployed on the robot to perform real-time detection and intelligent laser weeding. Test results demonstrate the superior performance of the proposed model: the precision of object detection reached 78. 09% (2. 54% over baseline) and that of keypoint detection stood at 80. 69% (8. 22% over baseline). The mean average precision (mAP50) metrics improved to 78. 14% and 80. 56%, representing increases of 2. 34% and 2. 88% respectively. Field tests achieved a 90. 2% weed control rate alongside a low 1. 9% damage rate to Salvia miltiorrhiza. These results validate the system's effectiveness and practicality, providing crucial technical support for intelligent weed management in Salvia miltiorrhiza and other high-value medicinal crops.

Details DOI

AAAI Conference 2025 Conference Paper

DIDiffGes: Decoupled Semi-Implicit Diffusion Models for Real-time Gesture Generation from Speech

Yongkang Cheng
Shaoli Huang
Xuelin Chen
Jifeng Ning
Mingming Gong

Diffusion models have demonstrated remarkable synthesis quality and diversity in generating co-speech gestures. However, the computationally intensive sampling steps associated with diffusion models hinder their practicality in real-world applications. Hence, we present DIDiffGes, for a Decoupled Semi-Implicit Diffusion model-based framework, that can synthesize high-quality, expressive gestures from speech using only a few sampling steps. Our approach leverages Generative Adversarial Networks (GANs) to enable large-step sampling for diffusion model. We decouple gesture data into body and hands distributions and further decompose them into marginal and conditional distributions. GANs model the marginal distribution implicitly, while L2 reconstruction loss learns the conditional distributions exciplictly. This strategy enhances GAN training stability and ensures expressiveness of generated full-body gestures. Our framework also learns to denoise root noise conditioned on local body representation, guaranteeing stability and realism. DIDiffGes can generate gestures from speech with just 10 sampling steps, without compromising quality and expressiveness, reducing the number of sampling steps by a factor of 100 compared to existing methods. Our user study reveals that our method outperforms state-of-the-art approaches in human likeness, appropriateness, and style correctness.

PDF Details DOI