Longform media such as movies have complex narrative structures, with events spanning a rich variety of ambient visual scenes. Domain specific challenges associated with visual scenes in movies include transitions, person coverage, and a wide array of real-life and fictional scenarios. Existing visual scene datasets in movies have limited taxonomies and don’t consider the visual scene transition within movie clips. In this work, we address the problem of visual scene recognition in movies by first automatically curating a new and extensive movie-centric taxonomy of 179 scene labels derived from movie scripts and auxiliary web-based video datasets. Instead of manual annotations which can be expensive, we use CLIP to weakly label 1.12 million shots from 32K movie clips based on our proposed taxonomy. We provide baseline visual models trained on the weakly labeled dataset called MovieCLIP and evaluate them on an independent dataset verified by human raters. We show that leveraging features from models pretrained on MovieCLIP benefits downstream tasks such as multi-label scene and genre classification of web videos and movie trailers.

The Joint Workshop on Aesthetic and Technical Quality Assessment of Multimedia and Media Analytics for Societal Trends (ATQAM/ MAST) aims to bring together researchers and professionals working in fields ranging from computer vision, multimedia computing, multimodal signal processing to psychology and social sciences. It is divided into two tracks: ATQAM and MAST. ATQAM track: Visual quality assessment techniques can be divided into image and video technical quality assessment (IQA and VQA, or broadly TQA) and aesthetics quality assessment (AQA). While TQA is a long-standing field, having its roots in media compression, AQA is relatively young. Both have received increased attention with developments in deep learning. The topics have mostly been studied separately, even though they deal with similar aspects of the underlying subjective experience of media. The aim is to bring together individuals in the two fields of TQA and AQA for the sharing of ideas and discussions on current trends, developments, issues, and future directions. MAST track: The research area of media content analytics has been traditionally used to refer to applications involving inference of higher-level semantics from multimedia content. However, multimedia is typically created for human consumption, and we believe it is necessary to adopt a human-centered approach to this analysis, which would not only enable a better understanding of how viewers engage with content but also how they impact each other in the process.

Given a Morse function f over a 2-manifold with or without boundary, the Reeb graph is obtained by contracting the connected components of the level sets to points. We prove tight upper and lower bounds on the number of loops in the Reeb graph that depend on the genus, the number of boundary components, and whether or not the 2-manifold is orientable. We also give an algorithm that constructs the Reeb graph in time O(nlogn), where n is the number of edges in the triangulation used to represent the 2-manifold and the Morse function.

This paper introduces two efficient algorithms that compute the Contour Tree of a 3D scalar field /spl Fscr/ and its augmented version with the Betti numbers of each isosurface. The Contour Tree is a fundamental data structure in scientific visualization that is used to preprocess the domain mesh to allow optimal computation of isosurfaces with minimal overhead storage. The Contour Tree can also be used to build user interfaces reporting the complete topological characterization of a scalar field. The first part of the paper presents a new scheme that augments the Contour Tree with the Betti numbers of each isocontour in linear time. We show how to extend the scheme with the Betti number computation without increasing its complexity. Thus, we improve on the time complexity from our previous approach from O(m log m) to O(n log n+m), where m is the number of tetrahedra and n is the number of vertices in the domain of /spl Fscr/. The second part of the paper introduces a new divide-and-conquer algorithm that computes the Augmented Contour Tree with improved efficiency. The central part of the scheme computes the output Contour Tree by merging two intermediate Contour Trees and is independent of the interpolant. In this way we confine any knowledge regarding a specific interpolant to an oracle that computes the tree for a single cell. We have implemented this oracle for the trilinear interpolant and plan to replace it with higher order interpolants when needed. The complexity of the scheme is O(n+t log n), where t is the number of critical points of /spl Fscr/. For the first time we can compute the Contour Tree in linear time in many practical cases when t=O(n/sup 1-/spl epsi//). Lastly, we report the running times for a parallel implementation of our algorithm, showing good scalability with the number of processors.