Deep convolutional networks have achieved great success for image recognition. However, for action recognition in videos, their advantage over traditional methods is not so evident. We present a general and flexible video-level framework for learning action models in videos. This method, called temporal segment network (TSN), aims to model long-range temporal structures with a new segment-based sampling and aggregation module. This unique design enables our TSN to efficiently learn action models by using the whole action videos. The learned models could be easily adapted for action recognition in both trimmed and untrimmed videos with simple average pooling and multi-scale temporal window integration, respectively. We also study a series of good practices for the instantiation of TSN framework given limited training samples. Our approach obtains the state-the-of-art performance on four challenging action recognition benchmarks: HMDB51 (71.0%), UCF101 (94.9%), THUMOS14 (80.1%), and ActivityNet v1.2 (89.6%). Using the proposed RGB difference for motion models, our method can still achieve competitive accuracy on UCF101 (91.0 %) while running at 340 FPS. Furthermore, based on the temporal segment networks, we won the video classification track at the ActivityNet challenge 2016 among 24 teams, which demonstrates the effectiveness of TSN and the proposed good practices.

With the availability of high frequent satellite data, crop phenology could be accurately mapped using time series spatial data. Vegetation index time-series data derived from AVHRR, MODIS, and SPOT-VEGETATION images usually have coarse spatial resolution. Mapping crop seasonality parameters using higher spatial resolution images (e.g., Landsat TM) is unprecedented. Recently launched HJ-1 A/B CCD sensors boarded on China Environment Satellite provided a feasible and ideal data source for the construction of high spatio-temporal resolution vegetation index time-series. This paper presented a comprehensive method to construct NDVI time-series dataset derived from HJ-1 A/B CCD and demonstrated its application in cropland areas. The procedures of time-series data construction included image preprocessing, signal filtering for time-series data, and interpolation for daily NDVI images then the NDVI time-series could present a complete and smooth phenological cycle. To demonstrate its application, TIMESAT program was employed to extract the seasonality parameters of crop lands located in Guanzhong Plain, China. The small-scale test showed that the crop seasonality parameters derived from HJ-1 A/B NDVI time-series were considerably accurate compared with local agro-metrological observation. Further study on technical issues regarding to time-series processing, and potential applications were discussed.

Over the past few years, three photorespiratory bypasses have been introduced into plants, two of which led to observable increases in photosynthesis and biomass yield. However, most of the experiments were carried out using Arabidopsis under controlled environmental conditions, and the increases were only observed under low-light and short-day conditions. In this study, we designed a new photorespiratory bypass (called GOC bypass), characterized by no reducing equivalents being produced during a complete oxidation of glycolate into CO 2 catalyzed by three rice-self-originating enzymes, i.e., glycolate oxidase, oxalate oxidase, and catalase. We successfully established this bypass in rice chloroplasts using a multi-gene assembly and transformation system. Transgenic rice plants carrying GOC bypass (GOC plants) showed significant increases in photosynthesis efficiency, biomass yield, and nitrogen content, as well as several other CO 2 -enriched phenotypes under both greenhouse and field conditions. Grain yield of GOC plants varied depending on seeding season and was increased significantly in the spring. We further demonstrated that GOC plants had significant advantages under high-light conditions and that the improvements in GOC plants resulted primarily from a photosynthetic CO 2 -concentrating effect rather than from improved energy balance. Taken together, our results reveal that engineering a newly designed chloroplastic photorespiratory bypass could increase photosynthetic efficiency and yield of rice plants grown in field conditions, particularly under high light.

No abstract