This paper presents the design and implementation of the SpiderWalk system for circumstance-aware transportation activity detection using a novel contact vibration sensor. Different from existing systems that only report the type of activity, our system detects not only the activity but also its circumstances (e.g., road surface, vehicle, and shoe types) to provide better support for applications such as activity logging, location tracking, and smart persuasive applications. Inspired by but different from existing audio-based context detection approaches using microphones, the SpiderWalk system is designed and implemented using an ultra-sensitive, flexible contact vibration sensor which mimics the spiders' sensory slit organs. By sensing vibration patterns from the soles of shoes, the system can accurately detect transportation activities with rich circumstance information while resisting undesirable external signals from other sources or speech that may cause the data assignment and privacy preserving issues. Moreover, our system is implemented by reusing existing audio devices and can be used by an unmodified smartphone, making it ready for large-scale deployments. Finally, a novel temporal and spatial correlated classification approach is proposed to accurately detect the complex combinations of transportation activities and circumstances based on the output of each individual classifiers. Experiments conducted on a real-world data set suggest our system can accurately detect different transportation activities and their circumstances with an average detection accuracy of 93.8% with resource overheads comparable to existing audio- and GPS-based systems.