We present GaussianAvatar, an efficient approach to creating realistic human avatars with dynamic 3D appearances from a single video. We start by introducing animatable 3D Gaussians to explicitly represent humans in various poses and clothing styles. Such an explicit and animatable representation can fuse 3D appearances more efficiently and consistently from 2D observations. Our representation is further augmented with dynamic properties to support pose-dependent appearance modeling, where a dynamic appearance network along with an optimizable feature tensor is designed to learn the motion-to-appearance mapping. Moreover, by leveraging the differentiable motion condition, our method enables a joint optimization of motions and appearances during avatar modeling, which helps to tackle the long-standing issue of inaccurate motion estimation in monocular settings. The efficacy of GaussianAvatar is validated on both the public dataset and our collected dataset, demonstrating its superior performances in terms of appearance quality and rendering efficiency.
Recent advancements in video-language understanding have been established on the foundation of image-text models, resulting in promising outcomes due to the shared knowledge between images and videos. However, video-language understanding presents unique challenges due to the inclusion of highly complex semantic details, which result in information redundancy, temporal dependency, and scene complexity. Current techniques have only partially tackled these issues, and our quantitative analysis indicates that some of these methods are complementary. In light of this, we propose a novel framework called RTQ (Refine, Temporal model, and Query), which addresses these challenges simultaneously. The approach involves refining redundant information within frames, modeling temporal relations among frames, and querying task-specific information from the videos. Remarkably, our model demonstrates outstanding performance even in the absence of video-language pre-training, and the results are comparable with or superior to those achieved by state-of-the-art pre-training methods.
Multimodal Large Language Models (MLLMs) have endowed LLMs with the ability to perceive and understand multi-modal signals. However, most of the existing MLLMs mainly adopt vision encoders pretrained on coarsely aligned image-text pairs, leading to insufficient extraction and reasoning of visual knowledge. To address this issue, we devise a dual-Level vIsual knOwledge eNhanced Multimodal Large Language Model (LION), which empowers the MLLM by injecting visual knowledge in two levels. 1) Progressive incorporation of fine-grained spatial-aware visual knowledge. We design a vision aggregator cooperated with region-level vision-language (VL) tasks to incorporate fine-grained spatial-aware visual knowledge into the MLLM. To alleviate the conflict between image-level and region-level VL tasks during incorporation, we devise a dedicated stage-wise instruction-tuning strategy with mixture-of-adapters. This progressive incorporation scheme contributes to the mutual promotion between these two kinds of VL tasks. 2) Soft prompting of high-level semantic visual evidence. We facilitate the MLLM with high-level semantic visual evidence by leveraging diverse image tags. To mitigate the potential influence caused by imperfect predicted tags, we propose a soft prompting method by embedding a learnable token into the tailored text instruction. Comprehensive experiments on several multi-modal benchmarks demonstrate the superiority of our model (e.g., improvement of 5% accuracy on VSR and 3% CIDEr on TextCaps over InstructBLIP, 5% accuracy on RefCOCOg over Kosmos-2).
Human-object interaction (HOI) detection aims at detecting human-object pairs and predicting their interactions. However, the complexity of human behavior and the diverse contexts in which these interactions occur make it challenging. Intuitively, human-centric visual cues, such as the involved participants, the body language, and the surrounding environment, play crucial roles in shaping these interactions. These cues are particularly vital in interpreting unseen interactions. In this paper, we propose three prompts with VLM to generate human-centric visual cues within an image from multiple perspectives of humans. To capitalize on these rich Human-Centric Visual Cues, we propose a novel approach named HCVC for HOI detection. Particularly, we develop a transformer-based multimodal fusion module with multitower architecture to integrate visual cue features into the instance and interaction decoders. Our extensive experiments and analysis validate the efficacy of leveraging the generated human-centric visual cues for HOI detection. Notably, the experimental results indicate the superiority of the proposed model over the existing state-of-the-art methods on two widely used datasets.
Text-to-video retrieval (TVR) aims to find the most relevant video in a large video gallery given a query text. The intricate and abundant context of the video challenges the performance and efficiency of TVR. To handle the serialized video contexts, existing methods typically select a subset of frames within a video to represent the video content for TVR. How to select the most representative frames is a crucial issue, whereby the selected frames are required to not only retain the semantic information of the video but also promote retrieval efficiency by excluding temporally redundant frames. In this paper, we make the first empirical study of frame selection for TVR. We systemically classify existing frame selection methods into text-free and text-guided ones, under which we detailedly analyze six different frame selections in terms of effectiveness and efficiency. Among them, two frame selections are first developed in this paper. According to the comprehensive analysis on multiple TVR benchmarks, we empirically conclude that the TVR with proper frame selections can significantly improve the retrieval efficiency without sacrificing the retrieval performance.
Teaching Visual Question Answering (VQA) models to refrain from answering unanswerable questions is necessary for building a trustworthy AI system. Existing studies, though have explored various aspects of VQA but somewhat ignored this particular attribute. This paper aims to bridge the research gap by contributing a comprehensive dataset, called UNK-VQA. The dataset is specifically designed to address the challenge of questions that models do not know. To this end, we first augment the existing data via deliberate perturbations on either the image or question. In specific, we carefully ensure that the question-image semantics remain close to the original unperturbed distribution. By this means, the identification of unanswerable questions becomes challenging, setting our dataset apart from others that involve mere image replacement. We then extensively evaluate the zero- and few-shot performance of several emerging multi-modal large models and discover their significant limitations when applied to our dataset. Additionally, we also propose a straightforward method to tackle these unanswerable questions. This dataset, we believe, will serve as a valuable benchmark for enhancing the abstention capability of VQA models, thereby leading to increased trustworthiness of AI systems. We have made the \href{https://github.com/guoyang9/UNK-VQA}{dataset} available to facilitate further exploration in this area.
Teaching Visual Question Answering (VQA) models to abstain from unanswerable questions is indispensable for building a trustworthy AI system. Existing studies, though have explored various aspects of VQA, yet marginally ignored this particular attribute. This paper aims to bridge the research gap by contributing a comprehensive dataset, called UNK-VQA. The dataset is specifically designed to address the challenge of questions that can be unanswerable. To this end, we first augment the existing data via deliberate perturbations on either the image or question. In specific, we carefully ensure that the question-image semantics remain close to the original unperturbed distribution. By means of this, the identification of unanswerable questions becomes challenging, setting our dataset apart from others that involve mere image replacement. We then extensively evaluate the zero- and few-shot performance of several emerging multi-modal large models and discover significant limitations of them when applied to our dataset. Additionally, we also propose a straightforward method to tackle these unanswerable questions. This dataset, we believe, will serve as a valuable benchmark for enhancing the abstention capability of VQA models, thereby leading to increased trustworthiness of AI systems.
In contrast to conventional visual question answering, video-grounded dialog necessitates a profound understanding of both dialog history and video content for accurate response generation. Despite commendable strides made by existing methodologies, they often grapple with the challenges of incrementally understanding intricate dialog histories and assimilating video information. In response to this gap, we present an iterative tracking and reasoning strategy that amalgamates a textual encoder, a visual encoder, and a generator. At its core, our textual encoder is fortified with a path tracking and aggregation mechanism, adept at gleaning nuances from dialog history that are pivotal to deciphering the posed questions. Concurrently, our visual encoder harnesses an iterative reasoning network, meticulously crafted to distill and emphasize critical visual markers from videos, enhancing the depth of visual comprehension. Culminating this enriched information, we employ the pre-trained GPT-2 model as our response generator, stitching together coherent and contextually apt answers. Our empirical assessments, conducted on two renowned datasets, testify to the prowess and adaptability of our proposed design.
Learning a versatile language-image model is computationally prohibitive under a limited computing budget. This paper delves into the efficient language-image pre-training, an area that has received relatively little attention despite its importance in reducing computational cost and footprint. To that end, we propose a vision token pruning and merging method, ie ELIP, to remove less influential tokens based on the supervision of language outputs. Our method is designed with several strengths, such as being computation-efficient, memory-efficient, and trainable-parameter-free, and is distinguished from previous vision-only token pruning approaches by its alignment with task objectives. We implement this method in a progressively pruning manner using several sequential blocks. To evaluate its generalization performance, we apply ELIP to three commonly used language-image pre-training models and utilize public image-caption pairs with 4M images for pre-training. Our experiments demonstrate that with the removal of ~30$\%$ vision tokens across 12 ViT layers, ELIP maintains significantly comparable performance with baselines ($\sim$0.32 accuracy drop on average) over various downstream tasks including cross-modal retrieval, VQA, image captioning, etc. In addition, the spared GPU resources by our ELIP allow us to scale up with larger batch sizes, thereby accelerating model pre-training and even sometimes enhancing downstream model performance. Our code will be released at https://github.com/guoyang9/ELIP.