No abstract

Person Re-Identification (Re-ID) is a very important task in video surveillance systems such as tracking people, finding people in public places, or analysing customer behavior in supermarkets. Although there have been many works to solve this problem, there are still remaining challenges such as large-scale datasets, imbalanced data, viewpoint, finegrained data (attributes), the Local Features are not employed at semantic level in online stage of Re-ID task, furthermore, the imbalanced data problem of attributes are not taken into consideration. This paper has proposed a Unified Re-ID system consisted of three main modules such as Pedestrian Attribute Ontology (PAO), Local Multi-task DCNN (Local MDCNN), Imbalance Data Solver (IDS). The new main point of our Re-ID system is the power of mutual support of PAO, Local MDCNN and IDS to exploit the inner-group correlations of attributes and pre-filter the mismatch candidates from Gallery set based on semantic information as Fashion Attributes and Facial Attributes, to solve the imbalanced data of attributes without adjusting network architecture and data augmentation. We experimented on the well-known Market1501 dataset. The experimental results have shown the effectiveness of our Re-ID system and it could achieve the higher performance on Market1501 dataset in comparison to some state-of-the-art Re-ID methods.

Vietnam’s Payment for Forest Ecosystem Services (PFES) scheme has the goal of protecting remaining natural forests by providing financial support to people involved in forest protection. However, studying the case of Dak Lak province in the Central Highlands region of Vietnam shows that even after eight years of PFES implementation, achieving this goal remains a challenge. Although PFES does provide a stable income source and higher payments than state forest protection programs, enables the mobilization of more personnel resources for patrolling forest and relieves a great burden on the state budget in terms of investment in forest protection and development, forest cover in Dak Lak province is still decreasing, mainly due to conversion for other land uses, especially commercial agricultural and industrial crops. These drivers are rooted in national socio-economic planning aimed at boosting economic growth and in local people’s need to sustain their livelihoods. In addition, our paper shows that illegal logging is still widespread in Dak Lak. Weak law enforcement in areas of forest managed by state forest authorities and state companies also contributes to deforestation. However, these drivers are neither fully recognized nor addressed, and instead, the blame for deforestation is laid on local communities. PFES alone cannot protect forests in Dak Lak province. It needs to be backed up by political commitment to address underlying drivers of deforestation, improved social programs to help local people diversify their income sources and clarity over land use.

No abstract

No abstract