Visual grounding is a task that seeks to predict the specific location of an object or region described by a linguistic expression within an image. Despite the recent success, existing methods still suffer from two problems. First, most methods use independently pre-trained unimodal feature encoders for extracting expressive feature embeddings, thus resulting in a significant semantic gap between unimodal embeddings and limiting the effective interaction of visual-linguistic contexts. Second, existing attention-based approaches equipped with the global receptive field have a tendency to neglect the local information present in the images. This limitation restricts the semantic understanding required to distinguish between referred objects and the background, consequently leading to inadequate localization performance. Inspired by the recent advance in knowledge distillation, in this paper, we propose a DUal knowlEdge disTillation (DUET) method for visual grounding models to bridge the cross-modal semantic gap and improve localization performance simultaneously. Specifically, we utilize the CLIP model as the teacher model to transfer the semantic knowledge to a student model, in which the vision and language modalities are linked into a unified embedding space. Besides, we design a self-distillation method for the student model to acquire localization knowledge by performing the region-level contrastive learning to make the predicted region close to the positive samples. To this end, this work further proposes a Semantics-Location Aware sampling mechanism to generate high-quality self-distillation samples. Extensive experiments on five datasets and ablation studies demonstrate the state-of-the-art performance of DUET and its orthogonality with different student models, thereby making DUET adaptable to a wide range of visual grounding architectures. Our code are available on DUET.

The precise characterization and modeling of Cyber-Physical-Social Systems (CPSS) requires more comprehensive and accurate data, which imposes heightened demands on intelligent sensing capabilities. To address this issue, Crowdsensing Intelligence (CSI) has been proposed to collect data from CPSS by harnessing the collective intelligence of a diverse workforce. Our first and second Distributed/Decentralized Hybrid Workshop on Crowdsensing Intelligence (DHW-CSI) have focused on principles and high-level processes of organizing and operating CSI, as well as the participants, methods, and stages involved in CSI. This perspective reports the outcomes of the latest DHW-CSI, focusing on Autonomous Crowdsensing (ACS) enabled by foundation intelligence and its associated technologies such as decentralized autonomous organizations and operations, large language models, and human-oriented operating systems. Specifically, we explain what ACS is and explore its distinctive features in comparison to traditional crowdsensing. Moreover, we present the “6A-goal” of ACS and propose potential avenues for future research.

A relatively simple and local interaction between individuals produces coordinated and ordered collective behaviors that are widespread at all levels of biological groups. Group chase and escape is an important aspect in the field of collective behavior, particularly in regard to predation events in species interactions. Compared with other aspects of collective behavior, less research has been performed on this aspect, and the existing models are constructed only from the phenomenological perspective. We present an individual-based model named Visual Perception-Decision-Propulsion to explore the group chase and escape of biological groups and define several evaluation indicators to assess different aspects of this problem. Within this model, 2 types of self-propulsion individuals, i.e., predators and prey, are considered, and we consider the alignment and repulsion term between homogeneous individuals. Chase and escape are described as the escape (or chase) term between heterogeneous individuals. Based on the model, we identify and distinguish between 2 capture patterns, i.e., cooperative capture and separative capture. Then, we control the internal parameters to analyze the condition of these 2 patterns for production, and the external empirical parameters are adjusted to explore their effect on these 2 patterns. Hence, this paper provides a novel model for group chase and escape based on biological vision to compensate for the shortcomings of classical models and help apply the characteristics of biological groups to human-made swarm systems in the case of confrontation.

The precise characterization and modeling of Cyber-Physical-Social Systems (CPSS) requires more comprehensive and accurate data, which imposes heightened demands on intelligent sensing capabilities. To address this issue, Crowdsensing Intelligence (CSI) has been proposed to collect data from CPSS by harnessing the collective intelligence of a diverse workforce. Our first and second Distributed/Decentralized Hybrid Workshop on Crowdsensing Intelligence (DHW-CSI) have focused on principles and high-level processes of organizing and operating CSI, as well as the participants, methods, and stages involved in CSI. This perspective reports the outcomes of the latest DHW-CSI, focusing on Autonomous Crowdsensing (ACS) enabled by foundation intelligence and its associated technologies such as decentralized autonomous organizations and operations, large language models, and human-oriented operating systems. Specifically, we explain what ACS is and explore its distinctive features in comparison to traditional crowdsensing. Moreover, we present the “6A-goal” of ACS and propose potential avenues for future research.