LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models

Recent open-vocabulary detectors achieve promising performance with abundant region-level annotated data. In this work, we show that an open-vocabulary detector co-training with a large language model by generating image-level detailed captions for each image can further improve performance. To achieve the goal, we first collect a dataset, GroundingCap-1M, wherein each image is accompanied by associated grounding labels and an image-level detailed caption. With this dataset, we finetune an open-vocabulary detector with training objectives including a standard grounding loss and a caption generation loss. We take advantage of a large language model to generate both region-level short captions for each region of interest and image-level long captions for the whole image. Under the supervision of the large language model, the resulting detector, LLMDet, outperforms the baseline by a clear margin, enjoying superior open-vocabulary ability. Further, we show that the improved LLMDet can in turn build a stronger large multi-modal model, achieving mutual benefits. The code, model, and dataset is available at https://github.com/iSEE-Laboratory/LLMDet.

HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding

In human-centric scenes, the ability to simultaneously understand visual and auditory information is crucial. While recent omni models can process multiple modalities, they generally lack effectiveness in human-centric scenes due to the absence of large-scale, specialized datasets and non-targeted architectures. In this work, we developed HumanOmni, the industry's first human-centric Omni-multimodal large language model. We constructed a dataset containing over 2.4 million human-centric video clips with detailed captions and more than 14 million instructions, facilitating the understanding of diverse human-centric scenes. HumanOmni includes three specialized branches for understanding different types of scenes. It adaptively fuses features from these branches based on user instructions, significantly enhancing visual understanding in scenes centered around individuals. Moreover, HumanOmni integrates audio features to ensure a comprehensive understanding of environments and individuals. Our experiments validate HumanOmni's advanced capabilities in handling human-centric scenes across a variety of tasks, including emotion recognition, facial expression description, and action understanding. Our model will be open-sourced to facilitate further development and collaboration within both academia and industry.

Omni-Emotion: Extending Video MLLM with Detailed Face and Audio Modeling for Multimodal Emotion Analysis

Understanding emotions accurately is essential for fields like human-computer interaction. Due to the complexity of emotions and their multi-modal nature (e.g., emotions are influenced by facial expressions and audio), researchers have turned to using multi-modal models to understand human emotions rather than single-modality. However, current video multi-modal large language models (MLLMs) encounter difficulties in effectively integrating audio and identifying subtle facial micro-expressions. Furthermore, the lack of detailed emotion analysis datasets also limits the development of multimodal emotion analysis. To address these issues, we introduce a self-reviewed dataset and a human-reviewed dataset, comprising 24,137 coarse-grained samples and 3,500 manually annotated samples with detailed emotion annotations, respectively. These datasets allow models to learn from diverse scenarios and better generalize to real-world applications. Moreover, in addition to the audio modeling, we propose to explicitly integrate facial encoding models into the existing advanced Video MLLM, enabling the MLLM to effectively unify audio and the subtle facial cues for emotion understanding. By aligning these features within a unified space and employing instruction tuning in our proposed datasets, our Omni-Emotion achieves state-of-the-art performance in both emotion recognition and reasoning tasks.

Facial Dynamics in Video: Instruction Tuning for Improved Facial Expression Perception and Contextual Awareness

Facial expression captioning has found widespread application across various domains. Recently, the emergence of video Multimodal Large Language Models (MLLMs) has shown promise in general video understanding tasks. However, describing facial expressions within videos poses two major challenges for these models: (1) the lack of adequate datasets and benchmarks, and (2) the limited visual token capacity of video MLLMs. To address these issues, this paper introduces a new instruction-following dataset tailored for dynamic facial expression caption. The dataset comprises 5,033 high-quality video clips annotated manually, containing over 700,000 tokens. Its purpose is to improve the capability of video MLLMs to discern subtle facial nuances. Furthermore, we propose FaceTrack-MM, which leverages a limited number of tokens to encode the main character's face. This model demonstrates superior performance in tracking faces and focusing on the facial expressions of the main characters, even in intricate multi-person scenarios. Additionally, we introduce a novel evaluation metric combining event extraction, relation classification, and the longest common subsequence (LCS) algorithm to assess the content consistency and temporal sequence consistency of generated text. Moreover, we present FEC-Bench, a benchmark designed to assess the performance of existing video MLLMs in this specific task. All data and source code will be made publicly available.

LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding

In this paper, we introduce LLaVA-Octopus, a novel video multimodal large language model. LLaVA-Octopus adaptively weights features from different visual projectors based on user instructions, enabling us to leverage the complementary strengths of each projector. We observe that different visual projectors exhibit distinct characteristics when handling specific tasks. For instance, some projectors excel at capturing static details, while others are more effective at processing temporal information, and some are better suited for tasks requiring temporal coherence. By dynamically adjusting feature weights according to user instructions, LLaVA-Octopus dynamically selects and combines the most suitable features, significantly enhancing the model's performance in multimodal tasks. Experimental results demonstrate that LLaVA-Octopus achieves excellent performance across multiple benchmarks, especially in tasks such as multimodal understanding, visual question answering, and video understanding, highlighting its broad application potential.

Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models

Recent vision foundation models can extract universal representations and show impressive abilities in various tasks. However, their application on object detection is largely overlooked, especially without fine-tuning them. In this work, we show that frozen foundation models can be a versatile feature enhancer, even though they are not pre-trained for object detection. Specifically, we explore directly transferring the high-level image understanding of foundation models to detectors in the following two ways. First, the class token in foundation models provides an in-depth understanding of the complex scene, which facilitates decoding object queries in the detector's decoder by providing a compact context. Additionally, the patch tokens in foundation models can enrich the features in the detector's encoder by providing semantic details. Utilizing frozen foundation models as plug-and-play modules rather than the commonly used backbone can significantly enhance the detector's performance while preventing the problems caused by the architecture discrepancy between the detector's backbone and the foundation model. With such a novel paradigm, we boost the SOTA query-based detector DINO from 49.0% AP to 51.9% AP (+2.9% AP) and further to 53.8% AP (+4.8% AP) by integrating one or two foundation models respectively, on the COCO validation set after training for 12 epochs with R50 as the detector's backbone.

DreamView: Injecting View-specific Text Guidance into Text-to-3D Generation

Text-to-3D generation, which synthesizes 3D assets according to an overall text description, has significantly progressed. However, a challenge arises when the specific appearances need customizing at designated viewpoints but referring solely to the overall description for generating 3D objects. For instance, ambiguity easily occurs when producing a T-shirt with distinct patterns on its front and back using a single overall text guidance. In this work, we propose DreamView, a text-to-image approach enabling multi-view customization while maintaining overall consistency by adaptively injecting the view-specific and overall text guidance through a collaborative text guidance injection module, which can also be lifted to 3D generation via score distillation sampling. DreamView is trained with large-scale rendered multi-view images and their corresponding view-specific texts to learn to balance the separate content manipulation in each view and the global consistency of the overall object, resulting in a dual achievement of customization and consistency. Consequently, DreamView empowers artists to design 3D objects creatively, fostering the creation of more innovative and diverse 3D assets. Code and model will be released at https://github.com/iSEE-Laboratory/DreamView.

Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition

Transformer-based methods have recently achieved great advancement on 2D image-based vision tasks. For 3D video-based tasks such as action recognition, however, directly applying spatiotemporal transformers on video data will bring heavy computation and memory burdens due to the largely increased number of patches and the quadratic complexity of self-attention computation. How to efficiently and effectively model the 3D self-attention of video data has been a great challenge for transformers. In this paper, we propose a Temporal Patch Shift (TPS) method for efficient 3D self-attention modeling in transformers for video-based action recognition. TPS shifts part of patches with a specific mosaic pattern in the temporal dimension, thus converting a vanilla spatial self-attention operation to a spatiotemporal one with little additional cost. As a result, we can compute 3D self-attention using nearly the same computation and memory cost as 2D self-attention. TPS is a plug-and-play module and can be inserted into existing 2D transformer models to enhance spatiotemporal feature learning. The proposed method achieves competitive performance with state-of-the-arts on Something-something V1 & V2, Diving-48, and Kinetics400 while being much more efficient on computation and memory cost. The source code of TPS can be found at https://github.com/MartinXM/TPS.

SP-ViT: Learning 2D Spatial Priors for Vision Transformers

Recently, transformers have shown great potential in image classification and established state-of-the-art results on the ImageNet benchmark. However, compared to CNNs, transformers converge slowly and are prone to overfitting in low-data regimes due to the lack of spatial inductive biases. Such spatial inductive biases can be especially beneficial since the 2D structure of an input image is not well preserved in transformers. In this work, we present Spatial Prior-enhanced Self-Attention (SP-SA), a novel variant of vanilla Self-Attention (SA) tailored for vision transformers. Spatial Priors (SPs) are our proposed family of inductive biases that highlight certain groups of spatial relations. Unlike convolutional inductive biases, which are forced to focus exclusively on hard-coded local regions, our proposed SPs are learned by the model itself and take a variety of spatial relations into account. Specifically, the attention score is calculated with emphasis on certain kinds of spatial relations at each head, and such learned spatial foci can be complementary to each other. Based on SP-SA we propose the SP-ViT family, which consistently outperforms other ViT models with similar GFlops or parameters. Our largest model SP-ViT-L achieves a record-breaking 86.3% Top-1 accuracy with a reduction in the number of parameters by almost 50% compared to previous state-of-the-art model (150M for SP-ViT-L vs 271M for CaiT-M-36) among all ImageNet-1K models trained on 224x224 and fine-tuned on 384x384 resolution w/o extra data.

Continual Local Replacement for Few-shot Image Recognition

The goal of few-shot learning is to learn a model that can recognize novel classes based on one or few training data. It is challenging mainly due to two aspects: (1) it lacks good feature representation of novel classes; (2) a few labeled data could not accurately represent the true data distribution. In this work, we use a sophisticated network architecture to learn better feature representation and focus on the second issue. A novel continual local replacement strategy is proposed to address the data deficiency problem. It takes advantage of the content in unlabeled images to continually enhance labeled ones. Specifically, a pseudo labeling strategy is adopted to constantly select semantic similar images on the fly. Original labeled images will be locally replaced by the selected images for the next epoch training. In this way, the model can directly learn new semantic information from unlabeled images and the capacity of supervised signals in the embedding space can be significantly enlarged. This allows the model to improve generalization and learn a better decision boundary for classification. Extensive experiments demonstrate that our approach can achieve highly competitive results over existing methods on various few-shot image recognition benchmarks.