Multi-Scale Contrastive Learning for Video Temporal Grounding

Temporal grounding, which localizes video moments related to a natural language query, is a core problem of vision-language learning and video understanding. To encode video moments of varying lengths, recent methods employ a multi-level structure known as a feature pyramid. In this structure, lower levels concentrate on short-range video moments, while higher levels address long-range moments. Because higher levels experience downsampling to accommodate increasing moment length, their capacity to capture information is reduced and consequently leads to degraded information in moment representations. To resolve this problem, we propose a contrastive learning framework to capture salient semantics among video moments. Our key methodology is to leverage samples from the feature space emanating from multiple stages of the video encoder itself requiring neither data augmentation nor online memory banks to obtain positive and negative samples. To enable such an extension, we introduce a sampling process to draw multiple video moments corresponding to a common query. Subsequently, by utilizing these moments' representations across video encoder layers, we instantiate a novel form of multi-scale and cross-scale contrastive learning that links local short-range video moments with global long-range video moments. Extensive experiments demonstrate the effectiveness of our framework for not only long-form but also short-form video grounding.

Motion-aware Contrastive Learning for Temporal Panoptic Scene Graph Generation

To equip artificial intelligence with a comprehensive understanding towards a temporal world, video and 4D panoptic scene graph generation abstracts visual data into nodes to represent entities and edges to capture temporal relations. Existing methods encode entity masks tracked across temporal dimensions (mask tubes), then predict their relations with temporal pooling operation, which does not fully utilize the motion indicative of the entities' relation. To overcome this limitation, we introduce a contrastive representation learning framework that focuses on motion pattern for temporal scene graph generation. Firstly, our framework encourages the model to learn close representations for mask tubes of similar subject-relation-object triplets. Secondly, we seek to push apart mask tubes from their temporally shuffled versions. Moreover, we also learn distant representations for mask tubes belonging to the same video but different triplets. Extensive experiments show that our motion-aware contrastive framework significantly improves state-of-the-art methods on both video and 4D datasets.

Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across multimodal tasks such as visual perception and reasoning, leading to good performance on various multimodal evaluation benchmarks. However, these benchmarks keep a static nature and overlap with the pre-training data, resulting in fixed complexity constraints and data contamination issues. This raises the concern regarding the validity of the evaluation. To address these two challenges, we introduce a dynamic multimodal evaluation protocol called Vision-Language Bootstrapping (VLB). VLB provides a robust and comprehensive assessment for LVLMs with reduced data contamination and flexible complexity. To this end, VLB dynamically generates new visual question-answering samples through a multimodal bootstrapping module that modifies both images and language, while ensuring that newly generated samples remain consistent with the original ones by a judge module. By composing various bootstrapping strategies, VLB offers dynamic variants of existing benchmarks with diverse complexities, enabling the evaluation to co-evolve with the ever-evolving capabilities of LVLMs. Extensive experimental results across multiple benchmarks, including SEEDBench, MMBench, and MME, show that VLB significantly reduces data contamination and exposes performance limitations of LVLMs.

PrefixQuant: Static Quantization Beats Dynamic through Prefixed Outliers in LLMs

Quantization is essential for deploying Large Language Models (LLMs) by enhancing memory efficiency and inference speed. Existing methods for activation quantization mainly address channel-wise outliers, often neglecting token-wise outliers, leading to reliance on costly per-token dynamic quantization. To address this, we introduce PrefixQuant, a novel technique that isolates outlier tokens offline without re-training. Specifically, PrefixQuant identifies high-frequency outlier tokens and prefixes them in the KV cache, preventing the generation of outlier tokens during inference and simplifying quantization. To our knowledge, PrefixQuant is the first to enable efficient per-tensor static quantization to outperform expensive per-token dynamic quantization. For instance, in W4A4KV4 (4- bit weight, 4-bit activation, and 4-bit KV cache) Llama-3-8B, PrefixQuant with per-tensor static quantization achieves a 7.43 WikiText2 perplexity and 71.08% average accuracy on 5 common-sense reasoning tasks, outperforming previous per-token dynamic quantization methods like QuaRot with 0.98 perplexity improvement and +5.98 points accuracy. Additionally, the inference speed of W4A4 quantized models using PrefixQuant is 1.60x to 2.81x faster than FP16 models and exceeds QuaRot models by 1.2x to 1.3x. Our code is available at \url{https://github.com/ChenMnZ/PrefixQuant}.

MM-Forecast: A Multimodal Approach to Temporal Event Forecasting with Large Language Models

We study an emerging and intriguing problem of multimodal temporal event forecasting with large language models. Compared to using text or graph modalities, the investigation of utilizing images for temporal event forecasting has not been fully explored, especially in the era of large language models (LLMs). To bridge this gap, we are particularly interested in two key questions of: 1) why images will help in temporal event forecasting, and 2) how to integrate images into the LLM-based forecasting framework. To answer these research questions, we propose to identify two essential functions that images play in the scenario of temporal event forecasting, i.e., highlighting and complementary. Then, we develop a novel framework, named MM-Forecast. It employs an Image Function Identification module to recognize these functions as verbal descriptions using multimodal large language models (MLLMs), and subsequently incorporates these function descriptions into LLM-based forecasting models. To evaluate our approach, we construct a new multimodal dataset, MidEast-TE-mm, by extending an existing event dataset MidEast-TE-mini with images. Empirical studies demonstrate that our MM-Forecast can correctly identify the image functions, and further more, incorporating these verbal function descriptions significantly improves the forecasting performance. The dataset, code, and prompts are available at https://github.com/LuminosityX/MM-Forecast.

GalleryGPT: Analyzing Paintings with Large Multimodal Models

Artwork analysis is important and fundamental skill for art appreciation, which could enrich personal aesthetic sensibility and facilitate the critical thinking ability. Understanding artworks is challenging due to its subjective nature, diverse interpretations, and complex visual elements, requiring expertise in art history, cultural background, and aesthetic theory. However, limited by the data collection and model ability, previous works for automatically analyzing artworks mainly focus on classification, retrieval, and other simple tasks, which is far from the goal of AI. To facilitate the research progress, in this paper, we step further to compose comprehensive analysis inspired by the remarkable perception and generation ability of large multimodal models. Specifically, we first propose a task of composing paragraph analysis for artworks, i.e., painting in this paper, only focusing on visual characteristics to formulate more comprehensive understanding of artworks. To support the research on formal analysis, we collect a large dataset PaintingForm, with about 19k painting images and 50k analysis paragraphs. We further introduce a superior large multimodal model for painting analysis composing, dubbed GalleryGPT, which is slightly modified and fine-tuned based on LLaVA architecture leveraging our collected data. We conduct formal analysis generation and zero-shot experiments across several datasets to assess the capacity of our model. The results show remarkable performance improvements comparing with powerful baseline LMMs, demonstrating its superb ability of art analysis and generalization. \textcolor{blue}{The codes and model are available at: https://github.com/steven640pixel/GalleryGPT.

Leveraging Weak Cross-Modal Guidance for Coherence Modelling via Iterative Learning

Cross-modal coherence modeling is essential for intelligent systems to help them organize and structure information, thereby understanding and creating content of the physical world coherently like human-beings. Previous work on cross-modal coherence modeling attempted to leverage the order information from another modality to assist the coherence recovering of the target modality. Despite of the effectiveness, labeled associated coherency information is not always available and might be costly to acquire, making the cross-modal guidance hard to leverage. To tackle this challenge, this paper explores a new way to take advantage of cross-modal guidance without gold labels on coherency, and proposes the Weak Cross-Modal Guided Ordering (WeGO) model. More specifically, it leverages high-confidence predicted pairwise order in one modality as reference information to guide the coherence modeling in another. An iterative learning paradigm is further designed to jointly optimize the coherence modeling in two modalities with selected guidance from each other. The iterative cross-modal boosting also functions in inference to further enhance coherence prediction in each modality. Experimental results on two public datasets have demonstrated that the proposed method outperforms existing methods for cross-modal coherence modeling tasks. Major technical modules have been evaluated effective through ablation studies. Codes are available at: \url{https://github.com/scvready123/IterWeGO}.

Exploring Deeper! Segment Anything Model with Depth Perception for Camouflaged Object Detection

This paper introduces a new Segment Anything Model with Depth Perception (DSAM) for Camouflaged Object Detection (COD). DSAM exploits the zero-shot capability of SAM to realize precise segmentation in the RGB-D domain. It consists of the Prompt-Deeper Module and the Finer Module. The Prompt-Deeper Module utilizes knowledge distillation and the Bias Correction Module to achieve the interaction between RGB features and depth features, especially using depth features to correct erroneous parts in RGB features. Then, the interacted features are combined with the box prompt in SAM to create a prompt with depth perception. The Finer Module explores the possibility of accurately segmenting highly camouflaged targets from a depth perspective. It uncovers depth cues in areas missed by SAM through mask reversion, self-filtering, and self-attention operations, compensating for its defects in the COD domain. DSAM represents the first step towards the SAM-based RGB-D COD model. It maximizes the utilization of depth features while synergizing with RGB features to achieve multimodal complementarity, thereby overcoming the segmentation limitations of SAM and improving its accuracy in COD. Experimental results on COD benchmarks demonstrate that DSAM achieves excellent segmentation performance and reaches the state-of-the-art (SOTA) on COD benchmarks with less consumption of training resources. The code will be available at https://github.com/guobaoxiao/DSAM.

Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning

Data quality stands at the forefront of deciding the effectiveness of video-language representation learning. However, video-text pairs in previous data typically do not align perfectly with each other, which might lead to video-language representations that do not accurately reflect cross-modal semantics. Moreover, previous data also possess an uneven distribution of concepts, thereby hampering the downstream performance across unpopular subjects. To address these problems, we propose a contrastive objective with a subtractive angular margin to regularize cross-modal representations in their effort to reach perfect similarity. Furthermore, to adapt to the non-uniform concept distribution, we propose a multi-layer perceptron (MLP)-parameterized weighting function that maps loss values to sample weights which enable dynamic adjustment of the model's focus throughout the training. With the training guided by a small amount of unbiased meta-data and augmented by video-text data generated by large vision-language model, we improve video-language representations and achieve superior performances on commonly used video question answering and text-video retrieval datasets.

Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models

Large language models (LLMs) have demonstrated impressive reasoning capabilities, particularly in textual mathematical problem-solving. However, existing open-source image instruction fine-tuning datasets, containing limited question-answer pairs per image, do not fully exploit visual information to enhance the multimodal mathematical reasoning capabilities of Multimodal LLMs (MLLMs). To bridge this gap, we address the lack of high-quality, diverse multimodal mathematical datasets by collecting 40K high-quality images with question-answer pairs from 24 existing datasets and synthesizing 320K new pairs, creating the MathV360K dataset, which enhances both the breadth and depth of multimodal mathematical questions. We introduce Math-LLaVA, a LLaVA-1.5-based model fine-tuned with MathV360K. This novel approach significantly improves the multimodal mathematical reasoning capabilities of LLaVA-1.5, achieving a 19-point increase and comparable performance to GPT-4V on MathVista's minitest split. Furthermore, Math-LLaVA demonstrates enhanced generalizability, showing substantial improvements on the MMMU benchmark. Our research highlights the importance of dataset diversity and synthesis in advancing MLLMs' mathematical reasoning abilities. The code and data are available at: \url{https://github.com/HZQ950419/Math-LLaVA}.