Zeqian Li

Zeqian Li, Yuwei Wang, Kexun Chen et al.

One-stage algorithm have been widely used in target detection systems that need to be trained with massive data. Most of them perform well both in real-time and accuracy. However, due to their convolutional structure, they need more computing power and greater memory consumption. Hence, we applied pruning strategy to target detection networks to reduce the number of parameters and the size of model. To demonstrate the practicality of the pruning method, we select the YOLOv5 model for experiments and provide a data set of outdoor obstacles to show the effect of model. In this specific data set, in the best circumstances, the volume of the network model is reduced by 49.7% compared with the original model, and the reasoning time is reduced by 52.5%. Meanwhile, it also uses data processing methods to compensate for the drop in accuracy caused by pruning.

Zeqian Li, Keyu Qiu, Chenxu Jiao et al.

This paper describes a French dialect recognition system that will appropriately distinguish between different regional French dialects. A corpus of five regions - Monaco, French-speaking, Belgium, French-speaking Switzerland, French-speaking Canada and France, which is targeted forconstruction by the Sketch Engine. The content of the corpus is related to the four themes of eating, drinking, sleeping and living, which are closely linked to popular life. The experimental results were obtained through the processing of a python coded pre-processor and Waikato Environment for Knowledge Analysis (WEKA) data analytic tool which contains many filters and classifiers for machine learning.

Chen Ju, Haicheng Wang, Zeqian Li et al.

Vision-Language Large Models (VLMs) have become primary backbone of AI, due to the impressive performance. However, their expensive computation costs, i.e., throughput and delay, impede potentials in real-world scenarios. To achieve acceleration for VLMs, most existing methods focus on the model perspective: pruning, distillation, quantification, but completely overlook the data-perspective redundancy. To fill the overlook, this paper pioneers the severity of data redundancy, and designs one plug-and-play Turbo module guided by information degree to prune inefficient tokens from visual or textual data. In pursuit of efficiency-performance trade-offs, information degree takes two key factors into consideration: mutual redundancy and semantic value. Concretely, the former evaluates the data duplication between sequential tokens; while the latter evaluates each token by its contribution to the overall semantics. As a result, tokens with high information degree carry less redundancy and stronger semantics. For VLMs' calculation, Turbo works as a user-friendly plug-in that sorts data referring to information degree, utilizing only top-level ones to save costs. Its advantages are multifaceted, e.g., being generally compatible to various VLMs across understanding and generation, simple use without retraining and trivial engineering efforts. On multiple public VLMs benchmarks, we conduct extensive experiments to reveal the gratifying acceleration of Turbo, under negligible performance drop.

Yibin Yan, Jilan Xu, Shangzhe Di et al.

Understanding continuous video streams plays a fundamental role in real-time applications including embodied AI and autonomous driving. Unlike offline video understanding, streaming video understanding requires the ability to process video streams frame by frame, preserve historical information, and make low-latency decisions. To address these challenges, our main contributions are three-fold. (i) We develop a novel streaming video backbone, termed as StreamFormer, by incorporating causal temporal attention into a pre-trained vision transformer. This enables efficient streaming video processing while maintaining image representation capability. (ii) To train StreamFormer, we propose to unify diverse spatial-temporal video understanding tasks within a multitask visual-language alignment framework. Hence, StreamFormer learns global semantics, temporal dynamics, and fine-grained spatial relationships simultaneously. (iii) We conduct extensive experiments on online action detection, online video instance segmentation, and video question answering. StreamFormer achieves competitive results while maintaining efficiency, demonstrating its potential for real-time applications.