The following technical report is available from http://aib.informatik.rwth-aachen.de: Sequence Level Salient Object Proposals for Generic Object Detection in Video Esther Horbert, Germán Martín García, Simone Frintrop, and Bastian Leibe AIB 2014-06 In this paper, we propose a novel approach for generating generic object proposals for object discovery and recognition in continuous monocular video. Such proposals have recently become a popular alternative to exhaustive window-based search as basis for classification. Contrary to previous approaches, we address the proposal generation problem at the level of entire video sequences instead of at the single image level. We propose a processing pipeline that starts from individual region proposals and tracks them over time. This enables to group proposals for similar objects and to automatically filter out inconsistent regions. For generating the per-frame proposals, we introduce a novel multi-scale saliency approach that achieves a higher per-frame recall with fewer proposals than current state-of-the-art methods. Taken together, those two components result in a significant reduction of the number of object candidates compared to frame level methods, while keeping a consistently high recall.