Informedia @ TRECVID2010

The Informedia group participated in four tasks this year, including Semantic indexing, Known-item search, Surveillance event detection and Event detection in Internet multimedia pilot. For semantic indexing, except for training traditional SVM classifiers for each high level feature by using different low level features, a kind of cascade classifier was trained which including four layers with different visual features respectively. For Known Item Search task, we built a text-based video retrieval and a visual-based video retrieval system, and then query-class dependent late fusion was used to combine the runs from these two systems. For surveillance event detection, we especially put our focus on analyzing motions and human in videos. We detected the events by three channels. Firstly, we adopted a robust new descriptor called MoSIFT, which explicitly encodes appearance features together with motion information. And then we trained event classifiers in sliding windows using a bag-of-video-word approach. Secondly, we used the human detection and tracking algorithms to detect and track the regions of human, and then just focus on the MoSIFT points in the human regions. Thirdly, after getting the decision, we also borrow the results of human detection to filter the decision. In addition, to reduce the number of false alarms further, we aggregated short positive windows to favor long segmentation and applied a cascade classifier approach. The performance shows dramatic improvement over last year on the event detection task. For event detection in internet multimedia pilot, our system is purely based on textual information in the form of Automatic Speech Recognition (ASR) and Optical Character Recognition (OCR). We submitted three runs; a run based on a simple combination of three different ASR transcripts, a run based on OCR only and a run that combines ASR and OCR. We noticed that both ASR and OCR contribute to the goals of this task. However the video collection is very challenging for those features, resulting in a low recall but high precision. 1 Semantic Indexing (SIN) In SIN task, we submit 4 runs this year. The first, the second and the forth runs are the full submissions whose results include all the 130 high level features. The third run is the light submission which submits the results for 10 high level features predifined. 1.1 Description of submissions • CMU1 1: MoSIFT feature only, trained with χ kernel for each high level feature. • CMU2 2: Select the low level feature which has best performance on training data and then train a classifier based on it. • CMU3 3: Cascade classifier is trained with four layers, and different layer is trained by using different visual feature. • CMU4 4: Linearly combine the prediction results of the classifiers trained on MoSIFT feature, SIFT feature, color feature, audio feature and face feature. 1.2 Details of submissions