With the explosion of video content on the Internet, there is a need for research on methods for video analysis which take human cognition into account. One such cognitive measure is memorability, or the ability to recall visual content after watching it. Prior research has looked into image memorability and shown that it is intrinsic to visual content, but the problem of modeling video memorability has not been addressed sufficiently. In this work, we develop a prediction model for video memorability, including complexities of video content in it. Detailed feature analysis reveals that the proposed method correlates well with existing findings on memorability. We also describe a novel experiment of predicting video sub-shot memorability and show that our approach improves over current memorability methods in this task. Experiments on standard datasets demonstrate that the proposed metric can achieve results on par or better than the state-of-the art methods for video summarization.

In this work, we propose the notion of a Parse Condition—a logical condition that is satisfiable if and only if a given string w can be successfully parsed using a grammar G. Further, we propose an algorithm for building an SMT encoding of such parse conditions for LL(1) grammars and demonstrate its utility by building two applications over it: automated repair of syntax errors in Tiger programs and automated parser synthesis to automatically synthesize LL(1) parsers from examples. We implement our ideas into a tool, Cyclops, that is able to successfully repair 80% of our benchmarks (675 buggy Tiger programs), clocking an average of 30 seconds per repair and synthesize parsers for interesting languages from examples. Like verification conditions (encoding a program in logic) have found widespread applications in program analysis, we believe that Parse Conditions can serve as a foundation for interesting applications in syntax analysis.

No abstract

No abstract

No abstract