Self-Supervised Video-Centralised Transformer for Video Face Clustering.

This article presents a novel method for face clustering in videos using a video-centralised transformer. Previous works often employed contrastive learning to learn frame-level representation and used average pooling to aggregate the features along the temporal dimension. This approach may not fully capture the complicated video dynamics. In addition, despite the recent progress in video-based contrastive learning, few have attempted to learn a self-supervised clustering-friendly face representation that benefits the video face clustering task. To overcome these limitations, our method employs a transformer to directly learn video-level representations that can better reflect the temporally-varying property of faces in videos, while we also propose a video-centralised self-supervised framework to train the transformer model. We also investigate face clustering in egocentric videos, a fast-emerging field that has not been studied yet in works related to face clustering. To this end, we present and release the first large-scale egocentric video face clustering dataset named EasyCom-Clustering. We evaluate our proposed method on both the widely used Big Bang Theory (BBT) dataset and the new EasyCom-Clustering dataset. Results show the performance of our video-centralised transformer has surpassed all previous state-of-the-art methods on both benchmarks, exhibiting a self-attentive understanding of face videos.

Toward Certified Robustness of Distance Metric Learning.

Metric learning aims to learn a distance metric such that semantically similar instances are pulled together while dissimilar instances are pushed away. Many existing methods consider maximizing or at least constraining a distance margin in the feature space that separates similar and dissimilar pairs of instances to guarantee their generalization ability. In this article, we advocate imposing an adversarial margin in the input space so as to improve the generalization and robustness of metric learning algorithms. We first show that the adversarial margin, defined as the distance between training instances and their closest adversarial examples in the input space, takes account of both the distance margin in the feature space and the correlation between the metric and triplet constraints. Next, to enhance robustness to instance perturbation, we propose to enlarge the adversarial margin through minimizing a derived novel loss function termed the perturbation loss. The proposed loss can be viewed as a data-dependent regularizer and easily plugged into any existing metric learning methods. Finally, we show that the enlarged margin is beneficial to the generalization ability by using the theoretical technique of algorithmic robustness. Experimental results on 16 datasets demonstrate the superiority of the proposed method over existing state-of-the-art methods in both discrimination accuracy and robustness against possible noise.

Jiaolong capsule protects SD rats against 2,4,6-trinitrobenzene sulfonic acid induced colitis.

ETHNOPHARMACOLOGICAL RELEVANCE: Jiaolong capsule (JLC) was approved for the therapy of gastrointestinal diseases by the State Food and Drug Administration (SFDA) of China. It has a satisfactory curative effect in the treatment of patients with inflammatory bowel disease, however, the mechanism remains to be elucidated. AIM OF THE STUDY: In current study, the effects and possible mechanisms of JLC on 2,4,6-trinitrobenzene sulfonic acid (TNBS)-induced colitis were investigated. MATERIALS AND METHODS: Sulfasalazine and JLC were administrated orally and initialized 6 h after TNBS enema, once a day for seven consecutive days. The effect of JLC on intestinal microbial populations and LPS/TLR-4/NF-κB pathway was observed and assessed. Thirty female SD rats were distributed into six groups randomly and equally, namely, control, TNBS, TNBS + sulfasalazine (625 mg/kg), and TNBS + three different doses of JLC (25, 50, and 100 mg/kg) groups. RESULTS: The effect of JLC on restoring normal structures of colorectum and repairing colonic damage were superior to that of sulfasalazine. JLC showed a positive effect in re-balancing intestinal bacteria population of colitis, and suppressed the activation of LPS/TLR-4/NF-κB pathway. CONCLUSION: The results suggest that JLC demonstrated a beneficial effect on treating colitis in a rat model. The possible mechanisms may be through the regulatory effect of intestinal commensal bacteria and down-regulation of LPS/TLR-4/NF-κB pathway.

Learning Local Metrics and Influential Regions for Classification.

The performance of distance-based classifiers heavily depends on the underlying distance metric, so it is valuable to learn a suitable metric from the data. To address the problem of multimodality, it is desirable to learn local metrics. In this short paper, we define a new intuitive distance with local metrics and influential regions, and subsequently propose a novel local metric learning algorithm called LMLIR for distance-based classification. Our key intuition is to partition the metric space into influential regions and a background region, and then regulate the effectiveness of each local metric to be within the related influential regions. We learn multiple local metrics and influential regions to reduce the empirical hinge loss, and regularize the parameters on the basis of a resultant learning bound. Encouraging experimental results are obtained from various public and popular data sets.