Search

Humans commonly work with multiple objects in daily life and can intuitively transfer manipulation skills to novel objects by understanding object functional regularities. However, existing technical approaches for analyzing and synthesizing hand-object manipulation are mostly limited to handling a single hand and object due to the lack of data support. To address this, we construct TACO, an extensive bimanual hand-object-interaction dataset spanning a large variety of tool-action-object compositions for daily human activities. TACO contains 2.5K motion sequences paired with third-person and egocentric views, precise hand-object 3D meshes, and action labels. To rapidly expand the data scale, we present a fully automatic data acquisition pipeline combining multi-view sensing with an optical motion capture system. With the vast research fields provided by TACO, we benchmark three generalizable hand-object-interaction tasks: compositional action recognition, generalizable hand-object motion forecasting, and cooperative grasp synthesis. Extensive experiments reveal new insights, challenges, and opportunities for advancing the studies of generalizable hand-object motion analysis and synthesis. Our data and code are available at https://taco2024.github.io.

Space-air-ground integrated networks (SAGINs), which have emerged as an expansion of terrestrial networks, provide flexible access, ubiquitous coverage, high-capacity backhaul, and emergency/disaster recovery for mobile users (MUs). While the massive benefits brought by SAGIN may improve the quality of service, unauthorized access to SAGIN entities is potentially dangerous. At present, conventional crypto-based authentication is facing challenges, such as the inability to provide continuous and transparent protection for MUs. In this article, we propose an AI-oriented two-phase multi-factor authentication scheme (ATMAS) by introducing intelligence to authentication. The satellite and network control center collaborate on continuous authentication, while unique spatial-temporal features, including service features and geographic features, are utilized to enhance the system security. Our further security analysis and performance evaluations show that ATMAS has proper security characteristics which can meet various security requirements. Moreover, we shed light on lightweight and efficient authentication mechanism design through a proper combination of spatial-temporal factors., Comment: Accepted by IEEE Consumer Electronics Magazine

Video captioning aims to generate natural language sentences that describe the given video accurately. Existing methods obtain favorable generation by exploring richer visual representations in encode phase or improving the decoding ability. However, the long-tailed problem hinders these attempts at low-frequency tokens, which rarely occur but carry critical semantics, playing a vital role in the detailed generation. In this paper, we introduce a novel Refined Semantic enhancement method towards Frequency Diffusion (RSFD), a captioning model that constantly perceives the linguistic representation of the infrequent tokens. Concretely, a Frequency-Aware Diffusion (FAD) module is proposed to comprehend the semantics of low-frequency tokens to break through generation limitations. In this way, the caption is refined by promoting the absorption of tokens with insufficient occurrence. Based on FAD, we design a Divergent Semantic Supervisor (DSS) module to compensate for the information loss of high-frequency tokens brought by the diffusion process, where the semantics of low-frequency tokens is further emphasized to alleviate the long-tailed problem. Extensive experiments indicate that RSFD outperforms the state-of-the-art methods on two benchmark datasets, i.e., MSR-VTT and MSVD, demonstrate that the enhancement of low-frequency tokens semantics can obtain a competitive generation effect. Code is available at https://github.com/lzp870/RSFD.

With the emergence of autonomous driving and 5G mobile communication systems, how to design vehicular networks to meet the requirements of ultra-reliable low-latency communication (URLLC) between autonomous vehicles is widely concerned by the academia and industry. In this paper, message transmission delay and reliability between autonomous vehicles based on millimeter wave (mmwave) multi-hop V2V communications under urban road environment are investigated. Considering the fact that vehicles cannot come arbitrarily close to each other, shifted-exponential distribution is proposed to model the headway distance (the distance between the head of a vehicle and the head of its follower). Simulation results show that message transmission delay and reliability decrease with the increase of the path loss exponent and are also affected by the minimum safe distance between adjacent vehicles.

5G vehicular communication is one of key enablers in next generation intelligent transportation system (ITS), that require ultra-reliable and low latency communication (URLLC). To meet this requirement, a new hybrid vehicular network structure which supports both centralized network structure and distributed structure is proposed in this paper. Based on the proposed network structure, a new vehicular network utility model considering the latency and reliability in vehicular networks is developed based on Euclidean norm theory. Building on the Pareto improvement theory in economics, a vehicular network uplink optimization algorithm is proposed to optimize the uplink utility of vehicles on the roads. Simulation results show that the proposed scheme can significantly improve the uplink vehicular network utility in vehicular networks to meet the URLLC requirements.

With the emerging of the fifth generation (5G) mobile communication systems, millimeter wave transmissions are believed to be a promising solution for vehicular networks, especially in vehicle to vehicle (V2V) communications. In millimeter wave V2V communications, different vehicular networking services have different quality requirements for V2V multi-hop links. To evaluate the quality of different V2V wireless links, a new link quality indicator is proposed in this paper considering requirements of the real-time and the reliability in V2V multi-hop links. Moreover, different weight factors are configured to reflect the different requirements of different types of services on real-time and reliability in the new quality indicator. Based on the proposed link quality indicator, the relationship between V2V link quality and one-hop communication distance under different vehicle densities is analyzed in this paper. Simulation results indicate that the link quality is improved with the increasing of vehicle density and there exists an optimal one-hop communication distance for the link quality when the vehicle density is fixed., Comment: 6 pages, 5 figures, reject by IEEE Globecom2017, re-submitted to WCSP2017

With the emerging of the fifth generation (5G) mobile communication systems and software defined networks, not only the performance of vehicular networks could be improved but also new applications of vehicular networks are required by future vehicles, e.g., pilotless vehicles. To meet requirements from intelligent transportation systems, a new vehicular network architecture integrated with 5G mobile communication technologies and software defined network is proposed in this paper. Moreover, fog cells have been proposed to flexibly cover vehicles and avoid frequently handover between vehicles and road side units (RSUs). Based on the proposed 5G software defined vehicular networks, the transmission delay and throughput are analyzed and compared. Simulation results indicate that there exist a minimum transmission delay of 5G software defined vehicular networks considering different vehicle densities. Moreover, the throughput of fog cells in 5G software defined vehicular networks is better than the throughput of traditional transportation management systems.