Video object segmentation (VOS) is important for various computer vision problems, and handling it with minimal human supervision is highly desired for the large-scale applications. To bring down the supervision, existing approaches largely follow a data mining perspective by assuming the availability of multiple videos sharing the same object categories. It, however, would be problematic for the tasks that consume a single video. To address this problem, this paper proposes a novel approach that explores weakly labeled images to solve video object segmentation. Given a video labeled with a target category, images labeled with the same category are collected, from which noisy object exemplars are automatically discovered. After that the proposed approach extracts a set of region proposals on various frames and efficiently matches them with massive noisy exemplars in terms of appearance and spatial context. We then jointly select the best proposals across the video by solving a novel submodular problem that combines region voting and global region matching. Finally, the localization results are leveraged as strong supervision to guide pixel-level segmentation. Extensive experiments are conducted on two challenging public databases: Youtube-Objects and DAVIS. The results suggest that the proposed approach improves over previous weakly supervised/unsupervised approaches significantly, showing a performance even comparable with the several approaches supervised by the costly manual segmentations.

Trichloroethylene (TCE) is a ubiquitous chlorinated aliphatic hydrocarbon (CAH) in the environment, which is a Group 1 carcinogen with negative impacts on human health and ecosystems. Based on a series of recent advances, the environmental behavior and biodegradation process on TCE biodegradation need to be reviewed systematically. Four main biodegradation processes leading to TCE biodegradation by isolated bacteria and mixed cultures are anaerobic reductive dechlorination, anaerobic cometabolic reductive dichlorination, aerobic co-metabolism, and aerobic direct oxidation. More attention has been paid to the aerobic co-metabolism of TCE. Laboratory and field studies have demonstrated that bacterial isolates or mixed cultures containing Dehalococcoides or Dehalogenimonas can catalyze reductive dechlorination of TCE to ethene. The mechanisms, pathways, and enzymes of TCE biodegradation were reviewed, and the factors affecting the biodegradation process were discussed. Besides, the research progress on material-mediated enhanced biodegradation technologies of TCE through the combination of zero-valent iron (ZVI) or biochar with microorganisms was introduced. Furthermore, we reviewed the current research on TCE biodegradation in field applications, and finally provided the development prospects of TCE biodegradation based on the existing challenges. We hope that this review will provide guidance and specific recommendations for future studies on CAHs biodegradation in laboratory and field applications.

No abstract

No abstract