Guiding image segmentation with edge information is an often employed strategy in low level computer vision. To improve the trade-off between the sensitivity of homogeneous region delineation and the oversegmentation of the image, we have incorporated a recently proposed edge magnitudekonjidence map into a color image segmenter based on the mean shift procedure. The new method can recover regions with weak but sharp boundaries and thus can provide a more accurate input for high level interpretation modules. The Edge Detection and Image SegmentatiON (EDISON) system, available for download, iniplemerits the proposed technique andprovides a complete toolbox for discontinuity preserving filtering, segmentation and edge detection.

Abstract. Polygonal objects are prevalent in man-made scenes. Early approaches to detecting them relied mainly on geometry while subsequent ones also incorporated appearance-based cues. It has recently been shown that this could be done fast by searching for cycles in graphs of line-fragments, provided that the cycle scoring function can be expressed as additive terms attached to individual fragments. In this paper, we propose an approach that eliminates this restriction. Given a weighted linefragment graph, we use its cyclomatic number to partition the graph into managebly-sized sub-graphs that preserve nodes and edges with a high weight and are most likely to contain object contours. Object contours are then detected as maximally scoring elementary circuits enumerated in each sub-graph. Our approach can be used with any cycle scoring function and multiple candidates that share line fragments can be found. This is unlike in other approaches that rely on a greedy approach to finding candidates. We demonstrate that our approach significantly outperforms the state-of-the-art for the detection of building rooftops in aerial images and polygonal object categories from ImageNet.

Eye gaze offers several key cues regarding conversational discourse during face-to-face interaction between people. While a large body of research results exist to document the use of gaze in humanto-human interaction, and in animating realistic embodied avatars, recognition of conversational eye gestures-distinct eye movement patterns relevant to discourse-has received less attention. We analyze eye gestures during interaction with an animated embodied agent and propose a non-intrusive vision-based approach to estimate eye gaze and recognize eye gestures. In our user study, human participants avert their gaze (i.e. with "look-away" or "thinking" gestures) during periods of cognitive load. Using our approach, an agent can visually differentiate whether a user is thinking about a response or is waiting for the agent or robot to take its turn.

Abstract. In this paper we investigate the problem of exploiting multiple sources of information for object recognition tasks when additional modalities that are not present in the labeled training set are available for inference. This scenario is common to many robotics sensing applications and is in contrast with the assumption made by existing approaches that require at least some labeled examples for each modality. To leverage the previously unseen features, we make use of the unlabeled data to learn a mapping from the existing modalities to the new ones. This allows us to predict the missing data for the labeled examples and exploit all modalities using multiple kernel learning. We demonstrate the effectiveness of our approach on several multi-modal tasks including object recognition from multi-resolution imagery, grayscale and color images, as well as images and text. Our approach outperforms multiple kernel learning on the original modalities, as well as nearest-neighbor and bootstrapping schemes.