VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models
This addresses the need for better benchmarks in video-language research to assess temporal concept understanding, though it is incremental as it builds on existing evaluation frameworks.
The authors tackled the problem of evaluating temporal understanding in video-language models by introducing VITATECS, a diagnostic dataset with counterfactual descriptions, and found that current models are deficient in this area, with specific performance drops reported (e.g., up to 30% accuracy decrease on temporal tasks).
The ability to perceive how objects change over time is a crucial ingredient in human intelligence. However, current benchmarks cannot faithfully reflect the temporal understanding abilities of video-language models (VidLMs) due to the existence of static visual shortcuts. To remedy this issue, we present VITATECS, a diagnostic VIdeo-Text dAtaset for the evaluation of TEmporal Concept underStanding. Specifically, we first introduce a fine-grained taxonomy of temporal concepts in natural language in order to diagnose the capability of VidLMs to comprehend different temporal aspects. Furthermore, to disentangle the correlation between static and temporal information, we generate counterfactual video descriptions that differ from the original one only in the specified temporal aspect. We employ a semi-automatic data collection framework using large language models and human-in-the-loop annotation to obtain high-quality counterfactual descriptions efficiently. Evaluation of representative video-language understanding models confirms their deficiency in temporal understanding, revealing the need for greater emphasis on the temporal elements in video-language research.