Uncovering Hidden Challenges in Query-Based Video Moment Retrieval
This work highlights critical issues in evaluation for researchers in video understanding and natural language processing, though it is incremental as it focuses on dataset analysis rather than proposing a new method.
The paper investigates biases in benchmark datasets for query-based video moment retrieval, revealing that state-of-the-art models exhibit unexpected behaviors and that current benchmarks do not accurately reflect true progress in the task.
The query-based moment retrieval is a problem of localising a specific clip from an untrimmed video according a query sentence. This is a challenging task that requires interpretation of both the natural language query and the video content. Like in many other areas in computer vision and machine learning, the progress in query-based moment retrieval is heavily driven by the benchmark datasets and, therefore, their quality has significant impact on the field. In this paper, we present a series of experiments assessing how well the benchmark results reflect the true progress in solving the moment retrieval task. Our results indicate substantial biases in the popular datasets and unexpected behaviour of the state-of-the-art models. Moreover, we present new sanity check experiments and approaches for visualising the results. Finally, we suggest possible directions to improve the temporal sentence grounding in the future. Our code for this paper is available at https://mayu-ot.github.io/hidden-challenges-MR .