In the Eyes of the Beholder: The Effect of the Perceived Authenticity of Sanfang Qixiang in Fuzhou, China, among Locals and Domestic Tourists

Many historic and cultural heritage destinations have faced queries about authentic travel experiences and crises of commoditization related to tourism products. This study is based on the dyadic function of heritage destinations for both locals and domestic tourists: heritage as a spatial-temporal object for tourists, using authenticity as a theoretical framework. It examined the (1) effects of cultural motivations and prior knowledge on both object-based and existential authenticities, (2) effects of authenticity on destination experiences, and (3) moderating role of residential status on the relationship between authenticity and destination experience. The data were collected from 173 locals and 159 domestic tourists on site in the Sanfang Qixiang tourist district and analyzed using the SEM technique. The results indicated that cultural motivation and prior knowledge had significant effects on authenticity; however, only existential authenticity enhanced the destination experience, whereas object-based authenticity did not have an effect on the destination experience. In addition, residential status had a key moderating function in the relationship between the perception of authenticity and the destination experience. This study contributes to the literature by integrating the mutual gaze into heritage tourism literature and emphasizing the importance of a balance between authenticity and commoditization in heritage destination development in Asia. The findings hold some practical implications for the development of balanced management strategies to minimize potential conflicts and maximize user satisfaction with heritage tourism.

SPATIO-TEMPORAL OBJECT STABILITY FOR MONITORING EVOLVING AREAS IN SATELLITE IMAGE TIME SERIES

Monitoring observable processes in Satellite Image Time Series (SITS) is one of the crucial way to understand dynamics of our planet that is facing unexpected behaviors due to climate change. In this paper, we propose a novel method to assess the evolution of objects (and especially their surface) through time. To do so, we first build a space-time tree representation of image time series. The so-called space-time tree is a hierarchical representation of an image sequences into a nested set of nodes characterizing the observed regions at multiple spatial and temporal scales. Then, we measure for each node the spatial area occupied at each time sample, and we focus on its evolution through time. We thus define the spatio-temporal stability of each node. We use this attribute to identify and measure changing areas in a remotely-sensed scene. We illustrate the purpose of our method with some experiments in a coastal environment using Sentinel-2 images, and in a flood occurred area with Sentinel-1 images.

Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Embeddings

Significant progress has been made recently in developing few-shot object segmentation methods. Learning is shown to be successful in few-shot segmentation settings, using pixel-level, scribbles and bounding box supervision. This paper takes another approach, i.e., only requiring image-level label for few-shot object segmentation. We propose a novel multi-modal interaction module for few-shot object segmentation that utilizes a co-attention mechanism using both visual and word embedding. Our model using image-level labels achieves 4.8% improvement over previously proposed image-level few-shot object segmentation. It also outperforms state-of-the-art methods that use weak bounding box supervision on PASCAL-5^i. Our results show that few-shot segmentation benefits from utilizing word embeddings, and that we are able to perform few-shot segmentation using stacked joint visual semantic processing with weak image-level labels. We further propose a novel setup, Temporal Object Segmentation for Few-shot Learning (TOSFL) for videos. TOSFL can be used on a variety of public video data such as Youtube-VOS, as demonstrated in both instance-level and category-level TOSFL experiments.

Motion-Attentive Transition for Zero-Shot Video Object Segmentation

In this paper, we present a novel Motion-Attentive Transition Network (MATNet) for zero-shot video object segmentation, which provides a new way of leveraging motion information to reinforce spatio-temporal object representation. An asymmetric attention block, called Motion-Attentive Transition (MAT), is designed within a two-stream encoder, which transforms appearance features into motion-attentive representations at each convolutional stage. In this way, the encoder becomes deeply interleaved, allowing for closely hierarchical interactions between object motion and appearance. This is superior to the typical two-stream architecture, which treats motion and appearance separately in each stream and often suffers from overfitting to appearance information. Additionally, a bridge network is proposed to obtain a compact, discriminative and scale-sensitive representation for multi-level encoder features, which is further fed into a decoder to achieve segmentation results. Extensive experiments on three challenging public benchmarks (i.e., DAVIS-16, FBMS and Youtube-Objects) show that our model achieves compelling performance against the state-of-the-arts. Code is available at: https://github.com/tfzhou/MATNet.