LVreID: Person Re-Identification with Long Sequence Videos
This paper mainly establishes a large-scale Long sequence Video database for person re-IDentification (LVreID).
arXiv subjects
Publications and source records attributed to Jianing Li.
This paper mainly establishes a large-scale Long sequence Video database for person re-IDentification (LVreID).
This paper proposes a two-stream convolution network to extract spatial and temporal cues for video based person Re-Identification (ReID). A temporal stream in this network is constructed by inserting several Multi-scale 3D (M3D) convolution layers into a 2D CNN network. The resulting M3D convolution network introduces a fraction of parameters into the 2D CNN, but gains the ability of multi-scale temporal feature learning. With this compact architecture, M3D convolution network is also more efficient and easier to optimize than existing 3D convolution networks. The temporal stream further involves Residual Attention Layers (RAL) to refine the temporal features. By jointly learning spatial-temporal attention masks in a residual manner, RAL identifies the discriminative spatial regions and temporal cues. The other stream in our network is implemented with a 2D CNN for spatial feature extraction. The spatial and temporal features from two streams are finally fused for the video based person ReID. Evaluations on three widely used benchmarks datasets, i.e., MARS, PRID2011, and iLIDS-VID demonstrate the substantial advantages of our method over existing 3D convolution networks and state-of-art methods.
Let $F$ be a number field. Let $p$ be a prime number. Washington proved the $\ell$-part of the class numbers in cyclotomic $\mathbb{Z}_p$ extension of $F$ is bounded when $F$ is an abelian number field and $\ell\neq p$ is a prime. By class number formula, this is essentially a mod $\ell$ nonvanishing property of Drichlet L-functions at $s=0$. In \cite{Sinnot}, Sinnot gave a different proof by algebraic methods. In this article, we show that Sinnot's method can prove nonvanishing properties of Drichlet L-functions at $s=-k$, where $k\geq 0$ is an integer. Since the Lichtenbaurn conjecture which relates the Dedekind zeta functions at $s=-k$ and higher K-groups is proved for abelian number fields, we give some bounded results on non-$p$ part of higher K-groups in cyclotomic $\mathbb{Z}_p$ extensions of a real abelian number field.
Feature extraction and matching are two crucial components in person Re-Identification (ReID). The large pose deformations and the complex view variations exhibited by the captured person images significantly increase the difficulty of learning and matching of the features from person images. To overcome these difficulties, in this work we propose a Pose-driven Deep Convolutional (PDC) model to learn improved feature extraction and matching models from end to end. Our deep architecture explicitly leverages the human part cues to alleviate the pose variations and learn robust feature representations from both the global image and different local parts. To match the features from global human body and local body parts, a pose driven feature weighting sub-network is further designed to learn adaptive feature fusions. Extensive experimental analyses and results on three popular datasets demonstrate significant performance improvements of our model over all published state-of-the-art methods.
We obtain new non-existence results of generalized bent functions from \ZZ^n_q to \ZZ_q (called type [n,q]). The first case is a class of types where q=2p_1^{r_1}p_2^{r_2}. The second case contains two types [1 <= n <= 3, 2 * 31^e]$ and [1 <= n <= 7,2 * 151^e].
We obtain new nonexistence results of generalized bent functions from $\{Z^n}_q$ to $\Z_q$ (called type $[n,q]$) in the case that there exist cyclotomic integers in $ \Z[ζ_{q}]$ with absolute value $q^{\frac{n}{2}}$. This result generalize the previous two scattered nonexistence results $[n,q]=[1,2\times7]$ of Pei \cite{Pei} and $[3,2\times 23^e]$ of Jiang-Deng \cite{J-D} to a generalized class. In the last section, we remark that this method can apply to the GBF from $\Z^n_2$ to $\Z_m$.