Person search aims at localizing and identifying a query person from a gallery of uncropped scene images. Different from person re-identification (re-ID), its performance also depends on the localization accuracy of a pedestrian detector. The state-of-the-art methods train the detector individually, and the detected bounding boxes may be suboptimal for the following re-ID task. To alleviate this issue, we propose a re-ID driven localization refinement framework for providing the refined detection boxes for person search. Specifically, we develop a differentiable ROI transform layer to effectively transform the bounding boxes from the original images. Thus, the box coordinates can be supervised by the re-ID training other than the original detection task. With this supervision, the detector can generate more reliable bounding boxes, and the downstream re-ID model can produce more discriminative embeddings based on the refined person localizations. Extensive experimental results on the widely used benchmarks demonstrate that our proposed method performs favorably against the stateof-the-art person search methods.

Recently, the sequence-to-sequence models have made remarkable progress on the task of keyphrase generation (KG) by concatenating multiple keyphrases in a predefined order as a target sequence during training. However, the keyphrases are inherently an unordered set rather than an ordered sequence. Imposing a predefined order will introduce wrong bias during training, which can highly penalize shifts in the order between keyphrases. In this work, we propose a new training paradigm ONE2SET without predefining an order to concatenate the keyphrases. To fit this paradigm, we propose a novel model that utilizes a fixed set of learned control codes as conditions to generate a set of keyphrases in parallel. To solve the problem that there is no correspondence between each prediction and target during training, we propose a K-step target assignment mechanism via bipartite matching, which greatly increases the diversity and reduces the duplication ratio of generated keyphrases. The experimental results on multiple benchmarks demonstrate that our approach significantly outperforms the state-of-the-art methods.

There is a growing interest in dataset generation recently due to the superior generative capacity of large pre-trained language models (PLMs). In this paper, we study a flexible and efficient zero-short learning method, ZE-ROGEN. Given a zero-shot task, we first generate a dataset from scratch using PLMs in an unsupervised manner. Then, we train a tiny task model (e.g., LSTM) under the supervision of the synthesized dataset. This approach allows highly efficient inference as the final task model only has orders of magnitude fewer parameters comparing to PLMs (e.g., GPT2-XL). Apart from being annotationfree and efficient, we argue that ZEROGEN can also provide useful insights from the perspective of data-free model-agnostic knowledge distillation, and unreferenced text generation evaluation. Experiments and analysis on different NLP tasks, namely, text classification, question answering, and natural language inference), show the effectiveness of ZEROGEN.

ObjectiveThis study aimed to evaluate retinal microvascular density in patients with Parkinson’s disease (PD) and its correlation with visual impairment.MethodsThis cross-sectional study included 24 eyes of 24 patients with PD and 23 eyes of 23 healthy controls. All participants underwent ophthalmic examination, visual evoked potential (VEP) test, 25-item National Eye Institute Visual Function Questionnaire (NEI VFQ-25), and optical coherence tomography angiography (OCTA) examination. The correlation between retinal microvascular density and visual parameter was evaluated using Spearman correlation analysis, and the area under receiver operating characteristic curve (AUROC) was calculated.ResultsParkinson’s disease patients had prolonged P100 latency (P = 0.041), worse vision-related quality of life (composite score and 3 of 12 subscales in NEI VFQ-25), and decreased vessel density (VD) in all sectors of 3-mm-diameter region (all P < 0.05) compared with healthy controls. There were no statistical differences in the ganglion cell-inner plexiform layer (GCIPL) thickness and retinal nerve fiber layer (RNFL) thickness between the two groups. A negative correlation was found between P100 latency and nasal and superior sectors of macular VD in a 3-mm-diameter region (r = −0.328, P = 0.030; r = −0.302, and P = 0.047, respectively). Macular VD in a 3-mm-diameter region showed diagnostic capacities to distinguish PD patients from healthy controls (AUROCs, ranging from 0.655 to 0.723).ConclusionThis study demonstrated that decreased retinal microvascular density was correlated with visual impairment in PD patients. Retinal microvasculature change may occur earlier than visual decline and retinal structure change and has the potential to be a promising diagnostic marker for early PD.

Document-level label consistency is an effective indicator that different occurrences of a particular token sequence are very likely to have the same entity types. Previous work focused on better context representations and used the CRF for label decoding. However, CRF-based methods are inadequate for modeling document-level label consistency. This work introduces a novel two-stage label refinement approach to handle document-level label consistency, where a key-value memory network is first used to record draft labels predicted by the base model, and then a multi-channel Transformer makes refinements on these draft predictions based on the explicit co-occurrence relationship derived from the memory network. In addition, in order to mitigate the side effects of incorrect draft labels, Bayesian neural networks are used to indicate the labels with a high probability of being wrong, which can greatly assist in preventing the incorrect refinement of correct draft labels. The experimental results on three named entity recognition benchmarks demonstrated that the proposed method significantly outperformed the state-of-the-art methods.