Zhihao Shuai, Yiyun Chen, Maolin Ma, Yutong Chen, Hanjia Qiu, Jing Xu, Ziye Chen, Weikai Yang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

In the noisy bars of contemporary large Chinese cities at night, young people sit around tables and “throw” gestures in the air as a form of playing social games. They engage in the rhythms and materialities of urban nightlife as a way of expressing their aesthetic pursuits and their notions of social power. Beyond entertainment, such activities are involved with multifaceted emotional and social layers of contemporary life, and they constitute culture – one that is not often understood, studied, or documented as such.

State-of-the-art lane detection methods often rely on specific knowledge about lanes – such as straight lines and parametric curves – to detect lane lines. While the specific knowledge can ease the modeling process, it poses challenges in handling lane lines with complex topologies (e.g., dense, forked, curved, etc.). Recently, dynamic convolution-based methods have shown promising performance by utilizing the features from some key locations of a lane line, such as the starting point, as convolutional kernels, and convoluting them with the whole feature map to detect lane lines. While such methods reduce the reliance on specific knowledge, the kernels computed from the key locations fail to capture the lane line’s global structure due to its long and thin structure, leading to inaccurate detection of lane lines with complex topologies. In addition, the kernels resulting from the key locations are sensitive to occlusion and lane intersections. To overcome these limitations, we propose a transformer-based dynamic kernel generation architecture for lane detection. It utilizes a transformer to generate dynamic convolutional kernels for each lane line in the input image, and then detect these lane lines with dynamic convolution. Compared to the kernels generated from the key locations of a lane line, the kernels generated with the transformer can capture the lane line’s global structure from the whole feature map, enabling them to effectively handle occlusions and lane lines with complex topologies. We evaluate our method on three lane detection benchmarks, and the results demonstrate its state-of-the-art performance. Specifically, our method achieves an F1 score of 63.40 on OpenLane and 88.47 on CurveLanes, surpassing the state of the art by 4.30 and 2.37 points, respectively.

Ziye Chen, Cheng Ding, Zusheng Zhang, Yanghui Rao, Haoran Xie. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Graph-based predictors have recently shown promising results on neural architecture search (NAS). Despite their efficiency, current graph-based predictors treat all operations equally, resulting in biased topological knowledge of cell architectures. Intuitively, not all operations are equally significant during forwarding propagation when aggregating information from these operations to another operation. To address the above issue, we propose a Hierarchical Operation-adaptive Predictor (HOP) for NAS. HOP contains an operation-adaptive attention module (OAM) to capture the diverse knowledge between operations by learning the relative significance of operations in cell architectures during aggregation over iterations. In addition, a cell-hierarchical gated module (CGM) further refines and enriches the obtained topological knowledge of cell architectures, by integrating cell information from each iteration of OAM. The experimental results compared with state-of-the-art predictors demonstrate the capability of our proposed HOP.

In this paper, we aim to enhance self-attention (SA) mechanism for deep metric learning in visual perception, by capturing richer contextual dependencies in visual data. To this end, we propose a novel module, named compressed self-attention (CSA), which significantly reduces the computation and memory cost with a neglectable decrease in accuracy with respect to the original SA mechanism, thanks to the following two characteristics: i) it only needs to compute a small number of base attention maps for a small number of base feature vectors; and ii) the output at each spatial location can be simply obtained by an adaptive weighted average of the outputs calculated from the base attention maps. The high computational efficiency of CSA enables the application to high-resolution shallow layers in convolutional neural networks with little additional cost. In addition, CSA makes it practical to further partition the feature maps into groups along the channel dimension and compute attention maps for features in each group separately, thus increasing the diversity of long-range dependencies and accordingly boosting the accuracy. We evaluate the performance of CSA via extensive experiments on two metric learning tasks: person re-identification and local descriptor learning. Qualitative and quantitative comparisons with latest methods demonstrate the significance of CSA in this topic.

Mixed counting models that use the negative binomial distribution as the prior can well model over-dispersed and hierarchically dependent random variables; thus they have attracted much attention in mining dispersed document topics. However, the existing parameter inference method like Monte Carlo sampling is quite time-consuming. In this paper, we propose two efficient neural mixed counting models, i.e., the Negative Binomial-Neural Topic Model (NB-NTM) and the Gamma Negative Binomial-Neural Topic Model (GNB-NTM) for dispersed topic discovery. Neural variational inference algorithms are developed to infer model parameters by using the reparameterization of Gamma distribution and the Gaussian approximation of Poisson distribution. Experiments on real-world datasets indicate that our models outperform state-of-the-art baseline models in terms of perplexity and topic coherence. The results also validate that both NB-NTM and GNB-NTM can produce explainable intermediate variables by generating dispersed proportions of document topics.

In this paper, we apply self-attention (SA) mechanism to boost the performance of deep metric learning. However, due to the pairwise similarity measurement, the cost of storing and manipulating the complete attention maps makes it infeasible for large inputs. To solve this problem, we propose a compressed self-attention with low-rank approximation (CSALR) module, which significantly reduces the computation and memory costs without sacrificing the accuracy. In CSALR, the original attention map is decomposed into a landmark attention map and a combination coefficient map with a small number of landmark feature vectors sampled from the input feature map by average pooling. Thanks to the efficiency of CSALR, we can apply CSALR to high-resolution shallow convolutional layers and implement a multi-head form of CSALR, which further boosts the performance. We evaluate the proposed CSALR on person reidentification which is a typical metric learning task. Extensive experiments shows the effectiveness and efficiency of CSALR in deep metric learning and its superiority over the baselines.