Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models

Recent Multi-modal Large Language Models (MLLMs) have been challenged by the computational overhead resulting from massive video frames, often alleviated through compression strategies. However, the visual content is not equally contributed to user instructions, existing strategies (\eg, average pool) inevitably lead to the loss of potentially useful information. To tackle this, we propose the Hybrid-level Instruction Injection Strategy for Conditional Token Compression in MLLMs (HICom), utilizing the instruction as a condition to guide the compression from both local and global levels. This encourages the compression to retain the maximum amount of user-focused information while reducing visual tokens to minimize computational burden. Specifically, the instruction condition is injected into the grouped visual tokens at the local level and the learnable tokens at the global level, and we conduct the attention mechanism to complete the conditional compression. From the hybrid-level compression, the instruction-relevant visual parts are highlighted while the temporal-spatial structure is also preserved for easier understanding of LLMs. To further unleash the potential of HICom, we introduce a new conditional pre-training stage with our proposed dataset HICom-248K. Experiments show that our HICom can obtain distinguished video understanding ability with fewer tokens, increasing the performance by 2.43\% average on three multiple-choice QA benchmarks and saving 78.8\% tokens compared with the SOTA method. The code is available at https://github.com/lntzm/HICom.

SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability

Multimodal large language models (MLLMs) have made remarkable progress in either temporal or spatial localization. However, they struggle to perform spatio-temporal video grounding. This limitation stems from two major challenges. Firstly, it is difficult to extract accurate spatio-temporal information of each frame in the video. Secondly, the substantial number of visual tokens makes it challenging to precisely map visual tokens of each frame to their corresponding spatial coordinates. To address these issues, we introduce SpaceVLLM, a MLLM endowed with spatio-temporal video grounding capability. Specifically, we adopt a set of interleaved Spatio-Temporal Aware Queries to capture temporal perception and dynamic spatial information. Moreover, we propose a Query-Guided Space Decoder to establish a corresponding connection between the queries and spatial coordinates. Additionally, due to the lack of spatio-temporal datasets, we construct the Unified Spatio-Temporal Grounding (Uni-STG) dataset, comprising 480K instances across three tasks. This dataset fully exploits the potential of MLLM to simultaneously facilitate localization in both temporal and spatial dimensions. Extensive experiments demonstrate that SpaceVLLM achieves the state-of-the-art performance across 11 benchmarks covering temporal, spatial, spatio-temporal and video understanding tasks, highlighting the effectiveness of our approach. Our code, datasets and model will be released.

Rethinking Video Tokenization: A Conditioned Diffusion-based Approach

Video tokenizers, which transform videos into compact latent representations, are key to video generation. Existing video tokenizers are based on the VAE architecture and follow a paradigm where an encoder compresses videos into compact latents, and a deterministic decoder reconstructs the original videos from these latents. In this paper, we propose a novel \underline{\textbf{C}}onditioned \underline{\textbf{D}}iffusion-based video \underline{\textbf{T}}okenizer entitled \textbf{\ourmethod}, which departs from previous methods by replacing the deterministic decoder with a 3D causal diffusion model. The reverse diffusion generative process of the decoder is conditioned on the latent representations derived via the encoder. With a feature caching and sampling acceleration, the framework efficiently reconstructs high-fidelity videos of arbitrary lengths. Results show that {\ourmethod} achieves state-of-the-art performance in video reconstruction tasks using just a single-step sampling. Even a smaller version of {\ourmethod} still achieves reconstruction results on par with the top two baselines. Furthermore, the latent video generation model trained using {\ourmethod} also shows superior performance.

What Is a Good Caption? A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Coverage of MLLMs

Recent advancements in Multimodal Large Language Models (MLLMs) have rendered traditional visual captioning benchmarks obsolete, as they primarily evaluate short descriptions with outdated metrics. While recent benchmarks address these limitations by decomposing captions into visual elements and adopting model-based evaluation, they remain incomplete-overlooking critical aspects, while providing vague, non-explanatory scores. To bridge this gap, we propose CV-CapBench, a Comprehensive Visual Caption Benchmark that systematically evaluates caption quality across 6 views and 13 dimensions. CV-CapBench introduces precision, recall, and hit rate metrics for each dimension, uniquely assessing both correctness and coverage. Experiments on leading MLLMs reveal significant capability gaps, particularly in dynamic and knowledge-intensive dimensions. These findings provide actionable insights for future research. The code and data will be released.

Hallucination Mitigation Prompts Long-term Video Understanding

Recently, multimodal large language models have made significant advancements in video understanding tasks. However, their ability to understand unprocessed long videos is very limited, primarily due to the difficulty in supporting the enormous memory overhead. Although existing methods achieve a balance between memory and information by aggregating frames, they inevitably introduce the severe hallucination issue. To address this issue, this paper constructs a comprehensive hallucination mitigation pipeline based on existing MLLMs. Specifically, we use the CLIP Score to guide the frame sampling process with questions, selecting key frames relevant to the question. Then, We inject question information into the queries of the image Q-former to obtain more important visual features. Finally, during the answer generation stage, we utilize chain-of-thought and in-context learning techniques to explicitly control the generation of answers. It is worth mentioning that for the breakpoint mode, we found that image understanding models achieved better results than video understanding models. Therefore, we aggregated the answers from both types of models using a comparison mechanism. Ultimately, We achieved 84.2\% and 62.9\% for the global and breakpoint modes respectively on the MovieChat dataset, surpassing the official baseline model by 29.1\% and 24.1\%. Moreover the proposed method won the third place in the CVPR LOVEU 2024 Long-Term Video Question Answering Challenge. The code is avaiable at https://github.com/lntzm/CVPR24Track-LongVideo

Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval

Video Moment Retrieval (VMR) aims to retrieve temporal segments in untrimmed videos corresponding to a given language query by constructing cross-modal alignment strategies. However, these existing strategies are often sub-optimal since they ignore the modality imbalance problem, \textit{i.e.}, the semantic richness inherent in videos far exceeds that of a given limited-length sentence. Therefore, in pursuit of better alignment, a natural idea is enhancing the video modality to filter out query-irrelevant semantics, and enhancing the text modality to capture more segment-relevant knowledge. In this paper, we introduce Modal-Enhanced Semantic Modeling (MESM), a novel framework for more balanced alignment through enhancing features at two levels. First, we enhance the video modality at the frame-word level through word reconstruction. This strategy emphasizes the portions associated with query words in frame-level features while suppressing irrelevant parts. Therefore, the enhanced video contains less redundant semantics and is more balanced with the textual modality. Second, we enhance the textual modality at the segment-sentence level by learning complementary knowledge from context sentences and ground-truth segments. With the knowledge added to the query, the textual modality thus maintains more meaningful semantics and is more balanced with the video modality. By implementing two levels of MESM, the semantic information from both modalities is more balanced to align, thereby bridging the modality gap. Experiments on three widely used benchmarks, including the out-of-distribution settings, show that the proposed framework achieves a new start-of-the-art performance with notable generalization ability (e.g., 4.42% and 7.69% average gains of R1@0.7 on Charades-STA and Charades-CG). The code will be available at https://github.com/lntzm/MESM.