CogVLM2-Video

Zhipu AI announced that it has trained a new video understanding model CogVLM2-Video and made it open source. It is reported that most current video understanding models use frame averaging and video tag compression methods, which leads to the loss of temporal information and cannot accurately answer time-related questions. Some models that focus on time question-answering datasets are too limited to specific formats and applicable fields, making the models lose a wider range of question-answering capabilities. ▲ Official effect demonstration Zhipu AI proposed a method for constructing automatic time positioning data based on visual models, generating 30,000 time-related…