One-shot object detection (OSOD) aims to detect all object instances towards the given category specified by a query image. Most existing studies in OSOD endeavor to establish effective cross-image correlation with limited query information, however, ignoring the problems of the model bias towards the base classes and the generalization degradation on the novel classes. Observing this, we propose a novel algorithm, namely Base-class Suppression with Prior Guidance (BSPG) network to achieve bias-free OSOD. Specifically, the objects of base categories can be detected by a base-class predictor and eliminated by a base-class suppression module (BcS). Moreover, a prior guidance module (PG) is designed to calculate the correlation of high-level features in a non-parametric manner, producing a class-agnostic prior map with unbiased semantic information to guide the subsequent detection process. Equipped with the proposed two modules, we endow the model with a strong discriminative ability to distinguish the target objects from distractors belonging to the base classes. Extensive experiments show that our method outperforms the previous techniques by a large margin and achieves new state-of-the-art performance under various evaluation settings.

The object of temporal action localization (TAL) is to predict the predefined action labels and the corresponding temporal boundary in a video. It can be found that TAL is a task of multi-modal modeling and highly dependent on the effect of temporal context representation. Inspired by this property, we propose an end-to-end local-to-global modeling architecture to learn the contextual consistency information in temporal sequence and cross-modal. Specifically, a local-to-global encoding Transformer is applied to model the video sequence to obtain video representation of different time scales. To achieve a reasonable balance between the specificity and correlation of different modalities, a cross semantic alignment (CSA) module is proposed to re-weight the encoded multi-model features by whether attending to the semantic correlations or specificity in different modalities. Further, to learn the trans-modal consistency from local to global and the uni-modal consistency belonging to the same category, the self-consistency learning (SCL) is designed to train the network. The experimental results demonstrate the significance of our method in major improvements upon prior works. Our model achieves 68.3% and 37.1% average mAPs on THUMOS14 and ActivityNet 1.3, outperforming state-of-the-art multi-stage and one-stage models.