科研成果 by Type: Conference Paper

Human action recognition is widely recognized as a challenging task due to the difficulty of effectively characterizing human action in a complex scene. Recent studies have shown that the dense-trajectory-based methods can achieve state-of-the-art recognition results on some challenging datasets. However, in these methods, each dense trajectory is often represented as a vector of coordinates, consequently losing the structural relationship between different trajectories. To address the problem, this paper proposes a novel Deep Trajectory Descriptor (DTD) for action recognition. First, we extract dense trajectories from multiple consecutive frames and then project them onto a canvas. This will result in a “trajectory texture” image which can effectively characterize the relative motion in these frames. Based on these trajectory texture images, a deep neural network (DNN) is utilized to learn a more compact and powerful representation of dense trajectories. In the action recognition system, the DTD descriptor, together with other non-trajectory features such as HOG, HOF and MBH, can provide an effective way to characterize human action from various aspects. Experimental results show that our system can statistically outperform several state-of-the-art approaches, with an average accuracy of 95:6% on KTH and an accuracy of 92.14% on UCF50.

Lucian’s short pamphlet Ἀλέξανδρος ἢ Ψευδόμαντις (Alexander, or The False Prophet) gives an account on how a conjurer by the name of Alexander concocted a syncretistic snake oracle to victimize Paphlagonians. Alexander met resistence, however. Lucian claims that Amastris in particular was Alexander’s most despised city in Pontus, because “the followers of Lepidus and others like them were numerous in the city; and he would never deliver an oracle to an Amastrian” (Luc. Alex. 25). While the snake oracle is widely attested on coins, statues and iconography, there is no corroborating evidence on Alexander of Abonuteichos and Lepidus of Amastris beyond Lucian’s text. Yet, scholars used two inscriptions mentioning a Tiberius Claudius Lepidus (CIG 4149 & 4150, now lost) to establish Lepidus as a historical figure (Robert 1980: 146; Marek 1993: 98; Gordon 1996: 114; Victor 1997: 151). The rationale behind this identification, however, seems to have only been based on the identical cognomen and the hypothesis that the inscribed Lepidus, being an archpriest of Pontus (ἀρχιερεύς τοὺ Πόντου), controlled both the sacred and the profane domains of Amastris. After a literature review concerning the historicity of Lucian’s Alexander and Lucian’s Lepidus, this paper presents a close reading of the Lepidus inscriptions from Amastris previous studies. Since previous studies seldom considered the definitions and functions of the different types of archpriesthood found in Amastris, this paper studies Amastrian inscriptions and associated literature to establish context. A reassessment of the hypothesis that Lepidus controlled the religious domain of Amastris during the Antonine period will conclude the paper.